Application of magnetic resonance diffusion kurtosis imaging for distinguishing histopathologic subtypes and grades of rectal carcinoma

Deep Learning for Medical Image-Based Cancer Diagnosis

(1) Background: The application of deep learning technology to realize cancer diagnosis based on medical images is one of the research hotspots in the field of artificial intelligence and computer vision. Due to the rapid development of deep learning methods, cancer diagnosis requires very high accuracy and timeliness as well as the inherent particularity and complexity of medical imaging. A comprehensive review of relevant studies is necessary to help readers better understand the current research status and ideas. (2) Methods: Five radiological images, including X-ray, ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission computed tomography (PET), and histopathological images, are reviewed in this paper. The basic architecture of deep learning and classical pretrained models are comprehensively reviewed. In particular, advanced neural networks emerging in recent years, including transfer learning, ensemble learning (EL), graph neural network, and vision transformer (ViT), are introduced. Five overfitting prevention methods are summarized: batch normalization, dropout, weight initialization, and data augmentation. The application of deep learning technology in medical image-based cancer analysis is sorted out. (3) Results: Deep learning has achieved great success in medical image-based cancer diagnosis, showing good results in image classification, image reconstruction, image detection, image segmentation, image registration, and image synthesis. However, the lack of high-quality labeled datasets limits the role of deep learning and faces challenges in rare cancer diagnosis, multi-modal image fusion, model explainability, and generalization. (4) Conclusions: There is a need for more public standard databases for cancer. The pre-training model based on deep neural networks has the potential to be improved, and special attention should be paid to the research of multimodal data fusion and supervised paradigm. Technologies such as ViT, ensemble learning, and few-shot learning will bring surprises to cancer diagnosis based on medical images.

Diffusion kurtosis imaging and MRI-detected extramural venous invasion in rectal cancer: correlation with clinicopathological prognostic factors

OBJECTIVE

To investigate the prognostic value of the diffusion kurtosis imaging (DKI)-derived parameters D value, K value, diffusion-weighted imaging (DWI) parameter apparent diffusion coefficient (ADC) value, and magnetic resonance imaging (MRI)-detected extramural venous invasion (EMVI) (mrEMVI) in rectal cancer patients.

METHODS

Forty patients who underwent MRI for rectal cancer were retrospectively evaluated. DKI-derived parameters D and K were measured using the Medical Imaging Interaction Toolkit. Conventional ADC values were measured from the corresponding DWI images. An experienced radiologist evaluated the mrEMVI status on MR images using the mrEMVI scoring system. An independent sample t-test or analysis of variance was used to analyze and compare the measurement data. The x² test or Fisher exact test was used for categorical variables. Receiver operating characteristic curves were used to assess the diagnostic performance of these parameters.

RESULTS

Among the 40 patients, MRI showed positive EMVI in 15 patients and negative EMVI in 25 patients. Positive mrEMVI status was associated with age, positive circumferential resection margin, pT-stage, lymphovascular invasion (LVI), distant metastasis, and serum carcinoembryonic antigen (CEA) level (P = 0.004-0.036). The dispersion coefficient (D) values and ADC values were significantly higher in the mucinous adenocarcinoma (MC) group than in the common adenocarcinoma (AC) group (P = 0.001), while kurtosis coefficient (K) values were lower in the MC group than in the AC group (P = 0.022). D values were significantly higher in the KRAS-mutated group than in the wild-type group (P < 0.05), whereas K values were lower in the KRAS-mutated group than in the wild-type group (P < 0.05). All three parameters (D, K, and ADC values) showed good diagnostic performance for discriminating MC from AC. Both the D and K values showed certain diagnostic performance for discriminating KRAS mutation.

CONCLUSION

DKI-derived parameters, conventional ADC values, and mrEMVI are associated with different histopathological prognostic factors. All DKI-derived parameters and conventional ADC values may distinguish MC from AC. DKI-derived parameters may also be used to discriminate KRAS mutation.

Native T1 mapping for differentiating the histopathologic type, grade, and stage of rectal adenocarcinoma: a pilot study

Background

Previous studies have indicated that T1 relaxation time could be utilized for the analysis of tissue characteristics. T1 mapping technology has been gradually used on research of body tumor. In this study, the application of native T1 relaxation time for differentiating the histopathologic type, grade, and stage of rectal adenocarcinoma was investigated.

Methods

One hundred and twenty patients with pathologically confirmed rectal adenocarcinoma were retrospectively evaluated. All patients underwent high-resolution anatomical magnetic resonance imaging (MRI), diffusion-weighted imaging (DWI), and T1 mapping sequences. Parameters of T1 relaxation time and apparent diffusion coefficient (ADC) were measured between the different groups. The diagnostic power was evaluated though the receiver operating characteristic (ROC) curve.

Results

The T1 and ADC values varied significantly between rectal mucinous adenocarcinoma (MC) and non-mucinous rectal adenocarcinoma (AC) ([1986.1 ± 163.3 ms] vs. [1562.3 ± 244.2 ms] and [1.38 ± 0.23 × 10⁻³mm²/s] vs. [1.03 ± 0.15 × 10⁻³mm²/s], respectively; P < 0.001). In the AC group, T1 relaxation time were significantly different between the low- and high-grade adenocarcinoma cases ([1508.7 ± 188.6 ms] vs. [1806.5 ± 317.5 ms], P < 0.001), while no differences were apparent in the ADC values ([1.03 ± 0.14 × 10⁻³mm²/s] vs. [1.04 ± 0.18 × 10⁻³mm²/s], P > 0.05). No significant differences in T1 and ADC values were identified between the different T and N stage groups for both MC and AC (all P > 0.05).

Conclusions

Native T1 relaxation time can be used to discriminate MC from AC. The T1 relaxation time was helpful for differentiating the low- and high-grade of AC.

Lymph Nodes Evaluation in Rectal Cancer: Where Do We Stand and Future Perspective

The assessment of nodal involvement in patients with rectal cancer (RC) is fundamental in disease management. Magnetic Resonance Imaging (MRI) is routinely used for local and nodal staging of RC by using morphological criteria. The actual dimensional and morphological criteria for nodal assessment present several limitations in terms of sensitivity and specificity. For these reasons, several different techniques, such as Diffusion Weighted Imaging (DWI), Intravoxel Incoherent Motion (IVIM), Diffusion Kurtosis Imaging (DKI), and Dynamic Contrast Enhancement (DCE) in MRI have been introduced but still not fully validated. Positron Emission Tomography (PET)/CT plays a pivotal role in the assessment of LNs; more recently PET/MRI has been introduced. The advantages and limitations of these imaging modalities will be provided in this narrative review. The second part of the review includes experimental techniques, such as iron-oxide particles (SPIO), and dual-energy CT (DECT). Radiomics analysis is an active field of research, and the evidence about LNs in RC will be discussed. The review also discusses the different recommendations between the European and North American guidelines for the evaluation of LNs in RC, from anatomical considerations to structured reporting.

T2*-weighted imaging and diffusion kurtosis imaging (DKI) of rectal cancer: correlation with clinical histopathologic prognostic factors

PURPOSE

Histopathologic prognostic factors of rectal cancer are closely associated with local recurrence and distant metastasis. We aim to investigate the feasibility of T2*WI in assessment of clinical prognostic factors of rectal cancer, and compare with DKI.

METHODS

This retrospective study enrolled 50 out of 205 patients with rectal cancer according to the inclusion criteria. The following parameters were obtained: R2* from T2*WI, mean diffusivity (MD_k), mean kurtosis (MK), and mean diffusivity (MD_t) from DKI using tensor method. Above parameters were compared by Mann-Whitney U-test or students' t test. Spearman correlations between different parameters and histopathological prognostic factors were determined. The diagnostic performances of R2* and DKI-derived parameters were analyzed by receiver operating characteristic curves (ROC), separately and jointly.

RESULTS

There were positive correlations between R2* and multiple prognostic factors of rectal cancer such as T category, N category, tumor grade, CEA level, and LVI (P < 0.004). MD_k and MD_t showed negative correlations with almost all the histopathological prognostic factors except CRM and TIL involvement (P < 0.003). MK correlated positively with the prognostic factors except CA19-9 level and CRM involvement (P < 0.006). The AUC ranges were 0.724-0.950 for R2* and 0.755-0.913 for DKI-derived parameters for differentiation of prognostic factors. However, no significant differences of diagnostic performance were found between T2*WI, DKI, or the combined imaging methods in characterizing rectal cancer.

CONCLUSION

R2* and DKI-derived parameters were associated with different histopathological prognostic factors, and might act as noninvasive biomarkers for histopathological characterization of rectal cancer.

Amide Proton Transfer Weighted and Intravoxel Incoherent Motion Imaging in Evaluation of Prognostic Factors for Rectal Adenocarcinoma

Objectives

To analyze the value of amide proton transfer (APT) weighted and intravoxel incoherent motion (IVIM) imaging in evaluation of prognostic factors for rectal adenocarcinoma, compared with diffusion weighted imaging (DWI).

Materials and Methods

Preoperative pelvic MRI data of 110 patients with surgical pathologically confirmed diagnosis of rectal adenocarcinoma were retrospectively evaluated. All patients underwent high-resolution T₂-weighted imaging (T₂WI), APT, IVIM, and DWI. Parameters including APT signal intensity (APT SI), pure diffusion coefficient (D), pseudo-diffusion coefficient (D*), perfusion fraction (f), and apparent diffusion coefficient (ADC) were measured in different histopathologic types, grades, stages, and structure invasion statuses. Receiver operating characteristic (ROC) curves were used to evaluate the diagnostic efficacy, and the corresponding area under the curves (AUCs) were calculated.

Results

APT SI, D and ADC values of rectal mucinous adenocarcinoma (MC) were significantly higher than those of rectal common adenocarcinoma (AC) ([3.192 ± 0.661%] vs. [2.333 ± 0.471%], [1.153 ± 0.238×10^-3 mm²/s] vs. [0.792 ± 0.173×10^-3 mm²/s], and [1.535 ± 0.203×10^-3 mm²/s] vs. [0.986 ± 0.124×10^-3 mm²/s], respectively; all P<0.001). In AC group, the APT SI and D values showed significant differences between low- and high-grade tumors ([2.226 ± 0.347%] vs. [2.668 ± 0.638%], and [0.842 ± 0.148×10^-3 mm²/s] vs. [0.777 ± 0.178×10^-3 mm²/s], respectively, both P<0.05). The D value had significant difference between positive and negative extramural vascular invasion (EMVI) tumors ([0.771 ± 0.175×10^-3 mm²/s] vs. [0.858 ± 0.151×10^-3 mm²/s], P<0.05). No significant difference of APT SI, D, D*, f or ADC was observed in different T stages, N stages, perineural and lymphovascular invasions (all P>0.05). The ROC curves showed that the AUCs of APT SI, D and ADC values for distinguishing MC from AC were 0.921, 0.893 and 0.995, respectively. The AUCs of APT SI and D values in distinguishing low- from high-grade AC were 0.737 and 0.663, respectively. The AUC of the D value for evaluating EMVI involvement was 0.646.

Conclusion

APT and IVIM were helpful to assess the prognostic factors related to rectal adenocarcinoma, including histopathological type, tumor grade and the EMVI status.

Diffusivity mapping of the ovaries: Variability of apparent diffusion and kurtosis variables over the menstrual cycle and influence of oral contraceptives

PURPOSE

We aimed to investigate whether quantitative diffusivity variables of healthy ovaries vary during the menstrual cycle and to evaluate alterations in women using oral contraceptives (OC).

METHODS

This prospective study (S-339/2016) included 30 healthy female volunteers, with (n = 15) and without (n = 15) intake of OC between 07/2017 and 09/2019. Participants underwent 3T diffusion-weighted MRI (b-values 0-2000 s/mm²) three times during a menstrual cycle (T1 = day 1-5; T2 = day 7-12; T3 = day 19-24). Both ovaries were manually three-dimensionally segmented on b = 1500 s/mm²; apparent diffusion coefficient (ADC) calculation and kurtosis fitting (D_app, K_app) were performed. Differences in ADC, D_app and K_app between time points and groups were compared using repeated measures ANOVA and t-test after Shapiro-Wilk and Brown-Forsythe test for normality and equal variance.

RESULTS

In women with a natural menstrual cycle, ADC and kurtosis variables showed significant changes in ovaries with the dominant follicle between T1 vs T2 and T1 vs T3, whilst no differences were observed between T2 vs T3: ADC ± SD for T1 1.524 ± 0.160, T2 1.737 ± 0.160, and T3 1.747 ± 0.241 μm²/ms (p = 0.01 T2 vs T1; p = 1.0 T2 vs T3, p = 0.003 T3 vs T1); D_app ± SD for T1 2.018 ± 0.140, T2 2.272 ± 0.189, and T3 2.230 ± 0.256 μm²/ms (p = 0.003 T2 vs T1, p = 1.0 T2 vs T3, p = 0.02 T3 vs T1); K_app ± SD for T1 0.614 ± 0.0339, T2 0.546 ± 0.0637, and T3 0.529 ± 0.0567 (p < 0.001 T2 vs T1, p = 0.86 T2 vs T3, p < 0.001 T3 vs T1). No significant differences were found in the contralateral ovaries or in females taking OC.

CONCLUSION

Physiological cycle-dependent changes in quantitative diffusivity variables of ovaries should be considered especially when interpreting radiomics analyses in reproductive women.

Application of diffusion kurtosis tensor MR imaging in characterization of renal cell carcinomas with different pathological types and grades

Background

To probe the feasibility and reproducibility of diffusion kurtosis tensor imaging (DKTI) in renal cell carcinoma (RCC) and to apply DKTI in distinguishing the subtypes of RCC and the grades of clear cell RCC (CCRCC).

Methods

Thirty-eight patients with pathologically confirmed RCCs [CCRCC for 30 tumors, papillary RCC (PRCC) for 5 tumors and chromophobic RCC (CRCC) for 3 tumors] were involved in the study. Diffusion kurtosis tensor MR imaging were performed with 3 b-values (0, 500, 1000s/mm²) and 30 diffusion directions. The mean kurtosis (MK), axial kurtosis (Ka), radial kurtosis (Kr) values and mean diffusity (MD) for RCC and contralateral normal parenchyma were acquired. The inter-observer agreements of all DKTI metrics of contralateral renal cortex and medulla were evaluated using Bland-Altman plots. Statistical comparisons with DKTI metrics of 3 RCC subtypes and between low-grade (Furman grade I ~ II, 22 cases) and high-grade (Furman grade III ~ IV, 8 cases) CCRCC were performed with ANOVA test and Student t test separately. Receiver operating characteristic (ROC) curve analyses were used to compare the diagnostic efficacy of DKTI metrics for predicting nuclear grades of CCRCC. Correlations between DKTI metrics and nuclear grades were also evaluated with Spearman correlation analysis.

Results

Inter-observer measurements for each metric showed great reproducibility with excellent ICCs ranging from 0.81 to 0.87. There were significant differences between the DKTI metrics of RCCs and contralateral renal parenchyma, also among the subtypes of RCC. MK and Ka values of CRCC were significantly higher than those of CCRCC and PRCC. Statistical difference of the MK, Ka, Kr and MD values were also obtained between CCRCC with high- and low-grades. MK values were more effective for distinguishing between low- and high- grade CCRCC (area under the ROC curve: 0.949). A threshold value of 0.851 permitted distinction with high sensitivity (90.9%) and specificity (87.5%).

Conclusion

Our preliminary results suggest a possible role of DKTI in differentiating CRCC from CCRCC and PRCC. MK, the principle DKTI metric might be a surrogate biomarker to predict nuclear grades of CCRCC.

Trial registration

ChiCTC, ChiCTR-DOD-17010833, Registered 10 March, 2017, retrospectively registered, http://www.chictr.org.cn/showproj.aspx?proj=17559.

Ultra-High-b-Value Kurtosis Imaging for Noninvasive Tissue Characterization of Ovarian Lesions

Background MRI with contrast material enhancement is the imaging modality of choice to evaluate sonographically indeterminate adnexal masses. The role of diffusion-weighted MRI, however, remains controversial. Purpose To evaluate the diagnostic performance of ultra-high-b-value diffusion kurtosis MRI in discriminating benign and malignant ovarian lesions. Materials and Methods This prospective cohort study evaluated consecutive women with sonographically indeterminate adnexal masses between November 2016 and December 2018. MRI at 3.0 T was performed, including diffusion-weighted MRI (b values of 0-2000 sec/mm²). Lesions were segmented on b of 1500 sec/mm² by two readers in consensus and an additional independent reader by using full-lesion segmentations on a single transversal slice. Apparent diffusion coefficient (ADC) calculation and kurtosis fitting were performed. Differences in ADC, kurtosis-derived ADC (D_app), and apparent kurtosis coefficient (K_app) between malignant and benign lesions were assessed by using a logistic mixed model. Area under the receiver operating characteristic curve (AUC) for ADC, D_app, and K_app to discriminate malignant from benign lesions was calculated, as was specificity at a sensitivity level of 100%. Results from two independent reads were compared. Histopathologic analysis served as the reference standard. Results A total of 79 ovarian lesions in 58 women (mean age ± standard deviation, 48 years ± 14) were evaluated. Sixty-two (78%) lesions showed benign and 17 (22%) lesions showed malignant histologic findings. ADC and D_app were lower and K_app was higher in malignant lesions: median ADC, D_app, and K_app were 0.74 µm²/msec (range, 0.52-1.44 µm²/msec), 0.98 µm²/msec (range, 0.63-2.12 µm²/msec), and 1.01 (range, 0.69-1.30) for malignant lesions, and 1.13 µm²/msec (range, 0.35-2.63 µm²/msec), 1.45 µm²/msec (range, 0.44-3.34 µm²/msec), and 0.65 (range, 0.44-1.43) for benign lesions (P values of .01, .02, < .001, respectively). AUC for K_app of 0.85 (95% confidence interval: 0.77, 0.94) was higher than was AUC from ADC of 0.78 (95% confidence interval: 0.67, 0.89; P = .047). Conclusion Diffusion-weighted MRI by using quantitative kurtosis variables is superior to apparent diffusion coefficient values in discriminating benign and malignant ovarian lesions and might be of future help in clinical practice, especially in patients with contraindication to contrast media application. © RSNA, 2020 Online supplemental material is available for this article.

Diffusion Kurtosis Imaging in the Assessment of Cervical Carcinoma

RATIONALE AND OBJECTIVES

To evaluate the additional value of diffusion kurtosis imaging (DKI) in the characterization of cervical carcinoma.

MATERIALS AND METHODS

Seventy-five patients (56.9 ± 13.4 years) with histologic-confirmed cervical carcinoma were included. Diffusion-weighted imaging (DWI) was acquired on a 3T MRI with five b values (0, 500, 800, 1000, and 1500 s/mm²). Data were analyzed based on DKI model (5 b values) and conventional DWI (0 and 1000 s/mm²). Largest single-slice region of interest (ROI) and volume of interest (VOI) were drawn around the tumor. Mean diffusivity (MD), mean kurtosis (MK), and apparent diffusion coefficient (ADC) of cervical carcinoma and normal myometrium were measured and compared. MD, MK, and ADC of cervical carcinoma were compared among histologic subtypes, tumor grades, and FIGO stages.

RESULTS

ROI- and VOI-derived DKI parameters and ADC were all in excellent consistency (intraclass correlation coefficient, ICC > 0.90, respectively). Cervical carcinoma had significantly lower MD, ADC, and higher MK than normal myometrium (p < 0.001). MD and ADC showed significant differences between histologic subtypes and FIGO stages, lower in squamous cell carcinoma than adenocarcinoma and higher in FIGO I-II than FIGO III-IV (p < 0.050), but not with tumor grade. No difference was observed in MK for different clinicopathologic features tested.

CONCLUSION

ROI and VOI analyses were in excellent consistency. MD and ADC were able to distinguish histologic subtypes and separating FIGO stages, MK could not. DKI showed no clear added value over conventional DWI in the characterization of cervical carcinoma.

Evaluation of diffusion kurtosis and diffusivity from baseline staging MRI as predictive biomarkers for response to neoadjuvant chemoradiation in locally advanced rectal cancer

PURPOSE

To evaluate the role of diffusion kurtosis and diffusivity as potential imaging biomarkers to predict response to neoadjuvant chemoradiation therapy (CRT) from baseline staging magnetic resonance imaging (MRI) in locally advanced rectal cancer (LARC).

MATERIALS AND METHODS

This retrospective study included 45 consecutive patients (31 male/14 female) who underwent baseline MRI with high b-value sequences (up to 1500 mm/s²) for LARC followed by neoadjuvant chemoradiation and surgical resection. The mean age was 57.4 years (range 34.2-72.9). An abdominal radiologist using open source software manually segmented T2-weighted images. Segmentations were used to derive diffusion kurtosis and diffusivity from diffusion-weighted images as well as volumetric data. These data were analyzed with regard to tumor regression grade (TRG) using the four-tier American Joint Committee on Cancer (AJCC) classification, TRG 0-3. Proportional odds regression was used to analyze the four-level ordinal outcome. A sensitivity analysis was performed using univariable logistic regression for binary TRG groups, TRG 0/1 (> 90% response), or TRG 2/3 (< 90% response). p < 0.05 was considered significant throughout.

RESULTS

In the univariable proportional odds regression analysis, higher diffusivity summary (D_sum) values were observed to be significantly associated with higher odds of being in one or more favorable TRG group (TRG 0 or 1). In other words, on average, patients with higher D_sum values were more likely to be in a more favorable TRG group. These results are mostly consistent with the sensitivity analysis, in which higher values for most D_sum values [all but region of interest (ROI)-max D median (p = 0.08)] were observed to be significantly associated with higher odds of being TRG 0 or 1. Tumor volume of interest (VOI) and ROI volume, ROI kurtosis mean and median, and VOI kurtosis mean and median were not significantly associated with TRG.

CONCLUSION

Diffusivity derived from the baseline staging MRI, but not diffusion kurtosis or volumetric data, is associated with TRG and therefore shows promise as a potential imaging biomarker to predict the response to neoadjuvant chemotherapy in LARC.

CLINICAL RELEVANCE STATEMENT

Diffusivity shows promise as a potential imaging biomarker to predict AJCC TRG following neoadjuvant CRT, which has implications for risk stratification. Patients with TRG 0/1 have 5-year disease-free survival (DFS) of 90-98%, as opposed to those who are TRG 2/3 with 5-year DFS of 68-73%.