The Novel Green Learning Artificial Intelligence for Prostate Cancer Imaging: A Balanced Alternative to Deep Learning and Radiomics

The application of artificial intelligence (AI) on prostate magnetic resonance imaging (MRI) has shown promising results. Several AI systems have been developed to automatically analyze prostate MRI for segmentation, cancer detection, and region of interest characterization, thereby assisting clinicians in their decision-making process. Deep learning, the current trend in imaging AI, has limitations including the lack of transparency "black box", large data processing, and excessive energy consumption. In this narrative review, the authors provide an overview of the recent advances in AI for prostate cancer diagnosis and introduce their next-generation AI model, Green Learning, as a promising solution.

A systematic review and meta-analysis of artificial intelligence diagnostic accuracy in prostate cancer histology identification and grading

BACKGROUND

Artificial intelligence (AI) is a promising tool in pathology, including cancer diagnosis, subtyping, grading, and prognostic prediction.

METHODS

The aim of the study is to assess AI application in prostate cancer (PCa) histology. We carried out a systematic literature search in 3 databases. Primary outcome was AI accuracy in differentiating between PCa and benign hyperplasia. Secondary outcomes were AI accuracy in determining Gleason grade and agreement among AI and pathologists.

RESULTS

Our final sample consists of 24 studies conducted from 2007 to 2021. They aggregate data from roughly 8000 cases of prostate biopsy and 458 cases of radical prostatectomy (RP). Sensitivity for PCa diagnostic exceeded 90% and ranged from 87% to 100%, and specificity varied from 68% to 99%. Overall accuracy ranged from 83.7% to 98.3% with AUC reaching 0.99. The meta-analysis using the Mantel-Haenszel method showed pooled sensitivity of 0.96 with I2 = 80.7% and pooled specificity of 0.95 with I2 = 86.1%. Pooled positive likehood ratio was 15.3 with I2 = 87.3% and negative - was 0.04 with I2 = 78.6%. SROC (symmetric receiver operating characteristics) curve represents AUC = 0.99. For grading the accuracy of AI was lower: sensitivity for Gleason grading ranged from 77% to 87%, and specificity from 82% to 90%.

CONCLUSIONS

The accuracy of AI for PCa identification and grading is comparable to expert pathologists. This is a promising approach which has several possible clinical applications resulting in expedite and optimize pathology reports. AI introduction into common practice may be limited by difficult and time-consuming convolutional neural network training and tuning.

Impact of persistent PSA after salvage radical prostatectomy: a multicenter study

BACKGROUND AND OBJECTIVE

Persistent prostatic specific antigen (PSA) represents a poor prognostic factor for recurrence after radical prostatectomy (RP). However, the impact of persistent PSA on oncologic outcomes in patients undergoing salvage RP is unknown. To investigate the impact of persistent PSA after salvage RP on long-term oncologic outcomes.

MATERIAL AND METHODS

Patients who underwent salvage RP for recurrent prostate cancer between 2000 and 2021 were identified from twelve high-volume centers. Only patients with available PSA after salvage RP were included. Kaplan-Meier analyses and multivariable Cox regression models were used to test the effect of persistent PSA on biochemical recurrence (BCR), metastasis and any death after salvage RP. Persistent PSA was defined as a PSA-value ≥ 0.1 ng/ml, at first PSA-measurement after salvage RP.

RESULTS

Overall, 580 patients were identified. Of those, 42% (n = 242) harbored persistent PSA. Median follow-up after salvage RP was 38 months, median time to salvage RP was 64 months and median time to first PSA after salvage RP was 2.2 months. At 84 months after salvage RP, BCR-free, metastasis-free, and overall survival was 6.6 vs. 59%, 71 vs. 88% and 77 vs. 94% for patients with persistent vs. undetectable PSA after salvage RP (all p < 0.01). In multivariable Cox models persistent PSA was an independent predictor for BCR (HR: 5.47, p < 0.001) and death (HR: 3.07, p < 0.01).

CONCLUSION

Persistent PSA is common after salvage RP and represents an independent predictor for worse oncologic outcomes. Patients undergoing salvage RP should be closely monitored after surgery to identify those with persistent PSA.

Increased N250 elicited by facial familiarity: An ERP study including the face inversion effect and facial emotion processing

The present study aims to explore how familiarity modulates the neural processing of faces under different conditions: upright or inverted, neutral or emotional. To this purpose, 32 participants (25 female; age: M = 27.7 years, SD = 9.3) performed two face/emotion identification tasks during EEG recording. In the first task, to study facial processing, three different categories of facial stimuli were presented during a target detection task: famous familiar faces, faces of loved ones, and unfamiliar faces. To explore the face inversion effect according to each level of familiarity, these facial stimuli were also presented upside down. In the second task, to study emotional face processing, an emotional identification task on personally familiar and unfamiliar faces was conducted. The behavioural results showed an improved performance in the identification of facial expressions of emotion with the increase of facial familiarity, consistent with the previous literature. Regarding electrophysiological results, we found increased amplitudes of the P100, N170, and N250 for inverted compared to upright faces, independently of their degree of familiarity. Moreover, we did not find familiarity effects at the P100 and N170 time-windows, but we found that N250 amplitude was larger for personally familiar compared to unfamiliar faces. This result supports the reasoning that the facial familiarity increases the neural activity during the N250 time-window, which may be explained by the processing of additional information prompted by the viewing of our loved ones faces, in contrast to what happens with unfamiliar individuals.

Transperineal vs transrectal magnetic resonance and ultrasound image fusion prostate biopsy: a pair-matched comparison

The objective of this study was to compare transperineal (TP) versus transrectal (TR) magnetic resonance imaging (MRI) and transrectal ultrasound (TRUS) fusion prostate biopsy (PBx). Consecutive men who underwent prostate MRI followed by a systematic biopsy. Additional target biopsies were performed from Prostate Imaging Reporting & Data System (PIRADS) 3-5 lesions. Men who underwent TP PBx were matched 1:2 with a synchronous cohort undergoing TR PBx by PSA, Prostate volume (PV) and PIRADS score. Endpoint of the study was the detection of clinically significant prostate cancer (CSPCa; Grade Group ≥ 2). Univariate and multivariable analyses were performed. Results were considered statistically significant if p < 0.05. Overall, 504 patients met the inclusion criteria. A total of 168 TP PBx were pair-matched to 336 TR PBx patients. Baseline demographics and imaging characteristics were similar between the groups. Per patient, the CSPCa detection was 2.1% vs 6.3% (p = 0.4) for PIRADS 1-2, and 59% vs 60% (p = 0.9) for PIRADS 3-5, on TP vs TR PBx, respectively. Per lesion, the CSPCa detection for PIRADS 3 (21% vs 16%; p = 0.4), PIRADS 4 (51% vs 44%; p = 0.8) and PIRADS 5 (76% vs 84%; p = 0.3) was similar for TP vs TR PBx, respectively. However, the TP PBx showed a longer maximum cancer core length (11 vs 9 mm; p = 0.02) and higher cancer core involvement (83% vs 65%; p < 0.001) than TR PBx. Independent predictors for CSPCa detection were age, PSA, PV, abnormal digital rectal examination findings, and PIRADS 3-5. Our study demonstrated transperineal MRI/TRUS fusion PBx provides similar CSPCa detection, with larger prostate cancer core length and percent of core involvement, than transrectal PBx.

Oncologic Outcomes of Lymph Node Dissection at Salvage Radical Prostatectomy

BACKGROUND

Lymph node invasion (LNI) represents a poor prognostic factor after primary radical prostatectomy (RP) for prostate cancer (PCa). However, the impact of LNI on oncologic outcomes in salvage radical prostatectomy (SRP) patients is unknown.

OBJECTIVE

To investigate the impact of lymph node dissection (LND) and pathological lymph node status (pNX vs. pN0 vs. pN1) on long-term oncologic outcomes of SRP patients.

PATIENTS AND METHODS

Patients who underwent SRP for recurrent PCa between 2000 and 2021 were identified from 12 high-volume centers. Kaplan-Meier analyses and multivariable Cox regression models were used. Endpoints were biochemical recurrence (BCR), overall survival (OS), and cancer-specific survival (CSS).

RESULTS

Of 853 SRP patients, 87% (n = 727) underwent LND, and 21% (n = 151) harbored LNI. The median follow-up was 27 months. The mean number of removed lymph nodes was 13 in the LND cohort. At 72 months after SRP, BCR-free survival was 54% vs. 47% vs. 7.2% for patients with pNX vs. pN0 vs. pN1 (p < 0.001), respectively. At 120 months after SRP, OS rates were 89% vs. 81% vs. 41% (p < 0.001), and CSS rates were 94% vs. 96% vs. 82% (p = 0.02) for patients with pNX vs. pN0 vs. pN1, respectively. In multivariable Cox regression analyses, pN1 status was independently associated with BCR (HR: 1.77, p < 0.001) and death (HR: 2.89, p < 0.001).

CONCLUSIONS

In SRP patients, LNI represents an independent poor prognostic factor. However, the oncologic benefit of LND in SRP remains debatable. These findings underline the need for a cautious LND indication in SRP patients as well as strict postoperative monitoring of SRP patients with LNI.

Patient-reported Satisfaction and Regret Following Focal Therapy for Prostate Cancer: A Prospective Multicenter Evaluation

Background

Several reports are available regarding the treatment decision regret of patients receiving conventional treatments for localized prostate cancer (PCa); yet data on patients undergoing focal therapy (FT) are sparse.

Objective

To evaluate the treatment decision satisfaction and regret among patients who underwent FT for PCa with high-intensity focused ultrasound (HIFU) or cryoablation (CRYO).

Design setting and participants

We identified consecutive patients who underwent HIFU or CRYO FT as the primary treatment for localized PCa at three US institutions. A survey with validated questionnaires, including the five-question Decision Regret Scale (DRS), International Prostate Symptom Score (IPSS), and International Index of Erectile Function (IIEF-5), was mailed to the patients. The regret score was calculated based on the five items of the DRS, and regret was defined as a DRS score of >25.

Outcome measurements and statistical analysis

Multivariable logistic regression models were applied to assess the predictors of treatment decision regret.

Results and limitations

Of 236 patients, 143 (61%) responded to the survey. Baseline characteristics were similar between responders and nonresponders. During a median (interquartile range) follow-up of 43 (26-68) mo, the treatment decision regret rate was 19.6%. On a multivariable analysis, higher prostate-specific antigen (PSA) at nadir after FT (odds ratio [OR] 1.48, 95% confidence interval [CI] 1.1-2, p = 0.009), presence of PCa on follow-up biopsy (OR 3.98, 95% CI 1.5-10.6, p = 0.006), higher post-FT IPSS (OR 1.18, 95% CI 1.01-1.37, p = 0.03), and newly diagnosed impotence (OR 6.67, 95% CI 1.57-27, p = 0.03) were independent predictors of treatment regret. The type of energy treatment (HIFU/CRYO) was not a predictor of regret/satisfaction. Limitations include retrospective abstraction.

Conclusions

FT for localized PCa is well accepted by the patients, with a low regret rate. Higher PSA at nadir, presence of cancer on follow-up biopsy, bothersome postoperative urinary symptoms, and impotence after FT were independent predictors of treatment decision regret.

Patient summary

In this report, we looked at the factors affecting satisfaction and regret in patients with prostate cancer undergoing focal therapy. We found that focal therapy is well accepted by the patients, while presence of cancer on follow-up biopsy as well as bothersome urinary symptoms and sexual dysfunction can predict treatment decision regret.

Transperineal Laser Ablation for Benign Prostatic Enlargement: A Systematic Review and Pooled Analysis of Pilot Studies

Transperineal laser ablation (TPLA) of the prostate is a new minimally invasive treatment option in men with lower urinary tract symptoms (LUTS) due to benign prostatic enlargement (BPE). The aim of this systematic review was to investigate the efficacy and safety of TPLA in the management of BPE. The primary outcomes were the improvement in urodynamic parameters (maximum urinary flow (Q_max) and postvoiding residue (PVR)) and LUTS relief, assessed using the IPSS questionnaire. The secondary outcomes were the preservation of sexual and ejaculatory functions, assessed with the IEEF-5 and MSHQ-EjD questionnaires, respectively, and rates of postoperative complications. We reviewed the literature for prospective or retrospective studies evaluating the use of TPLA in the treatment of BPE. A comprehensive search in PubMed, Scopus, Web of Science, and ClinicalTrials.gov was performed for English language articles published between January 2000 and June 2022. Pooled analysis of the included studies with available follow-up data for the outcomes of interest was additionally performed. After screening 49 records, six full-text manuscripts were identified, including two retrospective and four prospective non-comparative studies. Overall, 297 patients were included. All the studies independently reported a statistically significant improvement, from baseline, in Q_max, PVR, and IPSS score at each timepoint. Three studies additionally demonstrated that TPLA did not affect sexual function, reporting no change in the IEEF-5 score, and a statistically significant improvement in MSHQ-EjD score at each timepoint. Low rates of complications were recorded in all the included studies. Pooled analysis showed a clinically meaningful improvement in both micturition and sexual outcomes mean values at 1, 3, 6, and 12 months of follow-up, compared with baseline. Transperineal laser ablation of the prostate for the treatment of BPE showed interesting results in pilot studies. However, higher level and comparative studies are needed to confirm its efficacy in relieving obstructive symptoms and preserving sexual function.

Oligometastatic Prostate Cancer: Current Status and Future Challenges

In accordance with the spectrum theory of metastatic disease, an oligometastatic clinical state has been proposed as an intermediary step along the natural history of cancer with few (typically 1-3) metastatic lesions identifiable on imaging that may be amenable to metastasis-directed therapy. Effective therapy of oligometastatic disease is anticipated to impact cancer evolution by delaying progression and improving patient outcome at a minimal or acceptable cost of toxicity. There has been increasing recognition of oligometastatic disease in prostate cancer with the advent of new-generation imaging agents, most notably the recently approved PET radiotracers based on targeting prostate-specific membrane antigen. Early clinical trials with metastasis-directed therapy of oligometastases have provided evidence for delaying the employment of systematic therapy and improving outcome in selected patients. Despite these encouraging results, much needs to be investigated and learned about the underlying biology of the oligometastatic state along the evolutionary clinical course of prostate cancer, the identification of relevant imaging and nonimaging predictive and prognostic biomarkers, and the development of treatment strategies to optimize short-term and long-term patient outcome. We provide a review of the current status and the lingering challenges of this rapidly evolving clinical space in prostate cancer.

Multiparametric ultrasound of prostate: role in prostate cancer diagnosis

Recent advances in ultrasonography (US) technology established modalities, such as Doppler-US, HistoScanning, contrast-enhanced ultrasonography (CEUS), elastography, and micro-ultrasound. The early results of these US modalities have been promising, although there are limitations including the need for specialized equipment, inconsistent results, lack of standardizations, and external validation. In this review, we identified studies evaluating multiparametric ultrasonography (mpUS), the combination of multiple US modalities, for prostate cancer (PCa) diagnosis. In the past 5 years, a growing number of studies have shown that use of mpUS resulted in high PCa and clinically significant prostate cancer (CSPCa) detection performance using radical prostatectomy histology as the reference standard. Recent studies have demonstrated the role mpUS in improving detection of CSPCa and guidance for prostate biopsy and therapy. Furthermore, some aspects including lower costs, real-time imaging, applicability for some patients who have contraindication for magnetic resonance imaging (MRI) and availability in the office setting are clear advantages of mpUS. Interobserver agreement of mpUS was overall low; however, this limitation can be improved using standardized and objective evaluation systems such as the machine learning model. Whether mpUS outperforms MRI is unclear. Multicenter randomized controlled trials directly comparing mpUS and multiparametric MRI are warranted.

Future perspective of focal therapy for localized prostate cancer

Objective

To summarize the recent literature discussing focal therapy for localized prostate cancer.

Methods

A thorough literature review was performed using PubMed to identify recent studies involving focal therapy for the treatment of localized prostate cancer.

Results

In an effort to decrease the morbidity associated with prostate cancer treatment, many urologists are turning to focal therapy as an alternative treatment option. With this approach, the cancer bearing portion of the prostate is targeted while leaving the benign tissue untouched. Multiparametric magnetic resonance imaging remains the gold standard for visualization during focal therapy, but new imaging modalities such as prostate specific membrane antigen/positron emission tomography and contrast enhanced ultrasound are being investigated. Furthermore, several biomarkers, such as prostate cancer antigen 3 and prostate health index, are used in conjunction with imaging to improve risk stratification prior to focal therapy. Lastly, there are several novel technologies such as nanoparticles and transurethral devices that are under investigation for use in focal therapy.

Conclusion

Focal therapy is proving to be a promising option for the treatment of localized prostate cancer. However, further study is needed to determine the true efficacy of these exciting new technologies.

Comparative Effectiveness of Techniques in Targeted Prostate Biopsy

Simple Summary

Prostate cancer is one of the most common cancers in men. Traditionally, prostate cancer is diagnosed via transrectal ultrasound-guided prostate biopsy, using a systematic random template. Using multiparametric magnetic resonance imaging, lesions suspicious for prostate cancer can be identified, and subsequently targeted on biopsy, allowing for increased diagnostic accuracy. This article reviewed the current literature surrounding various types of targeted biopsy, such as transperineal biopsy, allowing for comparison not only between targeted biopsy and systematic biopsy, but also between different varieties of targeted biopsy.

Abstract

In this review, we evaluated literature regarding different modalities for multiparametric magnetic resonance imaging (mpMRI) and mpMRI-targeted biopsy (TB) for the detection of prostate cancer (PCa). We identified studies evaluating systematic biopsy (SB) and TB in the same patient, thereby allowing each patient to serve as their own control. Although the evidence supports the accuracy of TB, there is still a proportion of clinically significant PCa (csPCa) that is detected only in SB, indicating the importance of maintaining SB in the diagnostic pathway, albeit with additional cost and morbidity. There is a growing subset of data which supports the role of TB alone, which may allow for increased efficiency and decreased complications. We also compared the literature on transrectal (TR) vs. transperineal (TP) TB. Although further high-level evidence is necessary, current evidence supports similar csPCa detection rate for both approaches. We also evaluated various TB techniques such as cognitive fusion biopsy (COG-TB) and in-bore biopsy (IB-TB). COG-TB has comparable detection rates to software fusion, but is operator-dependent and may have reduced accuracy for smaller lesions. IB-TB may allow for greater precision as lesions are directly targeted; however, this is costly and time-consuming, and does not account for MRI-invisible lesions.

Multiparametric magnetic resonance imaging facilitates reclassification during active surveillance for prostate cancer

OBJECTIVE

To investigate the utility of multiparametric magnetic resonance imaging (mpMRI) in the reassessment and monitoring of patients on active surveillance (AS) for Grade Group (GG) 1 prostate cancer (PCa).

PATIENTS AND METHODS

We identified, from our prospectively maintained institutional review board-approved database, 181 consecutive men enrolled on AS for GG 1 PCa who underwent at least one surveillance mpMRI followed by MRI/prostate biopsy (PBx). A subset analysis was performed among 68 patients who underwent serial (at least two) mpMRI/PBx during AS. Pathological progression (PP) was defined as upgrade to GG ≥2 on follow up biopsy.

RESULTS

Baseline MRI was performed in 34 patients (19%). At a median follow-up of 2.2 years for the overall cohort, the PP was 12% (6/49) for Prostate Imaging Reporting and Data System (PI-RADS) 1-2 lesions and 37% (48/129) for the PI-RADS ≥3 lesions. The 2-year PP-free survival rate was 84%. Surveillance prostate-specific antigen density (P < 0.001) and surveillance PI-RADS ≥3 (P = 0.002) were independent predictors of PP on reassessment MRI/PBx. In the serial MRI cohort, the 2-year PP-free survival was 95% for the No-MRI-progression group vs 85% for the MRI-progression group (P = 0.02). MRI progression was significantly higher in the PP (62%) than in the No-PP (31%) group (P = 0.04). If serial MRI were used for PCa surveillance and biopsy were triggered based only on MRI progression, 63% of PBx might be postponed at the cost of missing 12% of GG ≥2 PCa in those with stable MRI. Conversely, this strategy would miss 38% of those with upgrading to GG ≥2 PCa on biopsy. Stable serial mpMRI correlates with no reclassification to GG ≥3 PCa during AS.

CONCLUSION

On surveillance mpMRI, PI-RADS ≥3 was associated with increased risk of PCa reclassification. Surveillance biopsy based only on MRI progression may avoid a large number of biopsies at the cost of missing many PCa reclassifications.

Current state of image-guided focal therapy for prostate cancer

PURPOSE

To review the current evidence regarding protocols and outcomes of image-guided focal therapy (FT) for prostate cancer (PCa).

METHODS

A literature search of the latest published studies assessing primary FT for PCa was carried out in Medline and Cochrane library databases followed by a critical review. FT modalities, follow-up strategies, and oncological and toxicity outcomes were summarized and discussed in this review.

RESULTS

Twenty-four studies with six different sources of energy met the inclusion criteria. A heterogeneity of patient selection, energy sources, treatment templates, and definitions of failure was found among the studies. While a third of patients may be found to have additional cancer burden over 3-5 years following FT, most patients will remain free of a radical procedure. The vast majority of patients maintain urinary continence and good erectile function after FT. Acute urinary retention is the most common complication, whilst severe complications remain rare.

CONCLUSION

An increasing number of prospective studies with longer follow-up have been recently published. Acceptable cancer control and low treatment toxicity after FT have been consistently reported. Follow-up imaging and routine biopsy must be encouraged post-FT. While there is no reliable PSA threshold to predict failure after FT, reporting post-FT positive biopsies and retreatment rates appear to be standard when assessing treatment efficacy.

Robotic Renal Artery Aneurysm Repair

BACKGROUND

Renal artery aneurysm (RAA) is a rare condition, traditionally managed with endovascular or open surgical techniques.

OBJECTIVE

To report our experience with robotic RAA repair.

DESIGN, SETTING, AND PARTICIPANTS

Nine consecutive patients underwent intracorporeal robotic surgery for 10 RAAs.

SURGICAL PROCEDURE

Two patients underwent concomitant robotic partial nephrectomy. One patient had RAA in a solitary kidney. Median RAA diameter was 2.2 (1.8-3)cm. Intracorporeal transarterial hypothermic renal perfusion was performed in five patients. Robotic techniques included tailored aneurysmectomy and repair (n=5), excision with end-to-end anastomosis (n=2), aneurysmectomy with branch reimplantation (n=1), prosthetic interposition graft repair (n=1), and simple nephrectomy (n=1; this patient's data were excluded from analysis).

MEASUREMENTS

Demographics, RAA characteristics, intraoperative techniques, perioperative outcomes, and follow up data were analyzed. Aneurysms were diagnosed by computed tomography, angiography, or incidentally during the performance of a partial nephrectomy.

RESULTS AND LIMITATIONS

All cases were performed robotically, without conversion to open surgery. Median (range) operative time was 3.8 (3-6)h, warm ischemia time 26 (19-32)min, hypothermic renal perfusion time 34 (29-69)min, and estimated blood loss 100 (25-400)ml. No intraoperative blood transfusion was required. Median hospital stay was 3 (2-6)d. One patient had a Clavien-Dindo grade II complication. At median follow-up of 16 (2-67)mo, all patients had preserved renal function. Follow-up imaging confirmed normal caliber reconstructed renal arteries with globally perfused kidneys, except for two kidneys with small segmental infarcts due to an intentionally ligated small polar vessel. Limitations include the small number of patients and the retrospective nature of the study.

CONCLUSIONS

Robotic repair of complex RAAs is feasible. Surgical expertise, patient selection, and RAA-specific vascular reconstruction are critical for success. Greater experience is needed to evaluate the proper place of robotic repair of RAAs.

PATIENT SUMMARY

We report intracorporeal robotic repair for complex renal artery aneurysms. This robotic operation is feasible and safe, and replicates open principles. However, it requires considerable experience and expertise.

Genomic and epidemiological monitoring of yellow fever virus transmission potential

The yellow fever virus (YFV) epidemic in Brazil is the largest in decades. The recent discovery of YFV in Brazilian Aedes species mosquitos highlights a need to monitor the risk of reestablishment of urban YFV transmission in the Americas. We use a suite of epidemiological, spatial, and genomic approaches to characterize YFV transmission. We show that the age and sex distribution of human cases is characteristic of sylvatic transmission. Analysis of YFV cases combined with genomes generated locally reveals an early phase of sylvatic YFV transmission and spatial expansion toward previously YFV-free areas, followed by a rise in viral spillover to humans in late 2016. Our results establish a framework for monitoring YFV transmission in real time that will contribute to a global strategy to eliminate future YFV epidemics.

Comparative diagnostic performance of TACT®slices and its multiple source images: anin vitrostudy

OBJECTIVE

To compare the diagnostic performances provided by tuned aperture computed tomography (TACT) slices and the multiple images that they originate from in the detection of primary caries on the proximal surfaces of posterior teeth.

STUDY DESIGN

Eight direct digital radiography images of each of 40 posterior teeth were acquired with a digital sensor. These source images were used to generate TACT slices of the teeth. Eight trained observers were calibrated in the use of both TACT slices and the eight source images of each tooth. They were asked to assess the presence/absence of proximal caries in the teeth using a 5-point rating scale. Observers' assessments were compared with the ground truth provided by histological examination of tooth sections. Areas under the receiver operating characteristic (ROC) curves (Az) were calculated for each combination of observer and image modality. Analysis of variance (ANOVA) was used to test the ROC values for potential statistical differences.

RESULTS

Mean ROC Az values were 0.760 for TACT slices and 0.771 for its multiple source images for the detection of primary proximal caries. ANOVA showed no statistically significant differences either between modalities (P = 0.656) or between observers (P = 0.851).

CONCLUSION

TACT slices and its multiple source images provide comparable diagnostic performance for proximal caries detection.