Color-coded visualization of magnetic resonance imaging multiparametric maps

Editorial for Special Topics: Imaging-Based Diagnosis for Prostate Cancer-State of the Art

This Special Topics Issue, "Imaging-based Diagnosis of Prostate Cancer-State of the Art", of Diagnostics compiles 10 select articles [...].

Myotubularin-related-protein-7 inhibits mutant (G12V) K-RAS by direct interaction

Inhibition of K-RAS effectors like B-RAF or MEK1/2 is accompanied by treatment resistance in cancer patients via re-activation of PI3K and Wnt signaling. We hypothesized that myotubularin-related-protein-7 (MTMR7), which inhibits PI3K and ERK1/2 signaling downstream of RAS, directly targets RAS and thereby prevents resistance. Using cell and structural biology combined with animal studies, we show that MTMR7 binds and inhibits RAS at cellular membranes. Overexpression of MTMR7 reduced RAS GTPase activities and protein levels, ERK1/2 phosphorylation, c-FOS transcription and cancer cell proliferation in vitro. We located the RAS-inhibitory activity of MTMR7 to its charged coiled coil (CC) region and demonstrate direct interaction with the gastrointestinal cancer-relevant K-RASG12V mutant, favouring its GDP-bound state. In mouse models of gastric and intestinal cancer, a cell-permeable MTMR7-CC mimicry peptide decreased tumour growth, Ki67 proliferation index and ERK1/2 nuclear positivity. Thus, MTMR7 mimicry peptide(s) could provide a novel strategy for targeting mutant K-RAS in cancers.

Classification of Gliomas and Germinomas of the Basal Ganglia by Transfer Learning

Background

Germ cell tumors (GCTs) are neoplasms derived from reproductive cells, mostly occurring in children and adolescents at 10 to 19 years of age. Intracranial GCTs are classified histologically into germinomas and non-germinomatous germ cell tumors. Germinomas of the basal ganglia are difficult to distinguish based on symptoms or routine MRI images from gliomas, even for experienced neurosurgeons or radiologists. Meanwhile, intracranial germinoma has a lower incidence rate than glioma in children and adults. Therefore, we established a model based on pre-trained ResNet18 with transfer learning to better identify germinomas of the basal ganglia.

Methods

This retrospective study enrolled 73 patients diagnosed with germinoma or glioma of the basal ganglia. Brain lesions were manually segmented based on both T1C and T2 FLAIR sequences. The T1C sequence was used to build the tumor classification model. A 2D convolutional architecture and transfer learning were implemented. ResNet18 from ImageNet was retrained on the MRI images of our cohort. Class activation mapping was applied for the model visualization.

Results

The model was trained using five-fold cross-validation, achieving a mean AUC of 0.88. By analyzing the class activation map, we found that the model's attention was focused on the peri-tumoral edema region of gliomas and tumor bulk for germinomas, indicating that differences in these regions may help discriminate these tumors.

Conclusions

This study showed that the T1C-based transfer learning model could accurately distinguish germinomas from gliomas of the basal ganglia preoperatively.

Weakly supervised annotation-free cancer detection and prediction of genotype in routine histopathology

Deep learning is a powerful tool in computational pathology: it can be used for tumor detection and for predicting genetic alterations based on histopathology images alone. Conventionally, tumor detection and prediction of genetic alterations are two separate workflows. Newer methods have combined them, but require complex, manually engineered computational pipelines, restricting reproducibility and robustness. To address these issues, we present a new method for simultaneous tumor detection and prediction of genetic alterations: The Slide-Level Assessment Model (SLAM) uses a single off-the-shelf neural network to predict molecular alterations directly from routine pathology slides without any manual annotations, improving upon previous methods by automatically excluding normal and non-informative tissue regions. SLAM requires only standard programming libraries and is conceptually simpler than previous approaches. We have extensively validated SLAM for clinically relevant tasks using two large multicentric cohorts of colorectal cancer patients, Darmkrebs: Chancen der Verhütung durch Screening (DACHS) from Germany and Yorkshire Cancer Research Bowel Cancer Improvement Programme (YCR-BCIP) from the UK. We show that SLAM yields reliable slide-level classification of tumor presence with an area under the receiver operating curve (AUROC) of 0.980 (confidence interval 0.975, 0.984; n = 2,297 tumor and n = 1,281 normal slides). In addition, SLAM can detect microsatellite instability (MSI)/mismatch repair deficiency (dMMR) or microsatellite stability/mismatch repair proficiency with an AUROC of 0.909 (0.888, 0.929; n = 2,039 patients) and BRAF mutational status with an AUROC of 0.821 (0.786, 0.852; n = 2,075 patients). The improvement with respect to previous methods was validated in a large external testing cohort in which MSI/dMMR status was detected with an AUROC of 0.900 (0.864, 0.931; n = 805 patients). In addition, SLAM provides human-interpretable visualization maps, enabling the analysis of multiplexed network predictions by human experts. In summary, SLAM is a new simple and powerful method for computational pathology that could be applied to multiple disease contexts. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons, Ltd. on behalf of The Pathological Society of Great Britain and Ireland.

Artificial Intelligence and Machine Learning in Prostate Cancer Patient Management-Current Trends and Future Perspectives

Artificial intelligence (AI) is the field of computer science that aims to build smart devices performing tasks that currently require human intelligence. Through machine learning (ML), the deep learning (DL) model is teaching computers to learn by example, something that human beings are doing naturally. AI is revolutionizing healthcare. Digital pathology is becoming highly assisted by AI to help researchers in analyzing larger data sets and providing faster and more accurate diagnoses of prostate cancer lesions. When applied to diagnostic imaging, AI has shown excellent accuracy in the detection of prostate lesions as well as in the prediction of patient outcomes in terms of survival and treatment response. The enormous quantity of data coming from the prostate tumor genome requires fast, reliable and accurate computing power provided by machine learning algorithms. Radiotherapy is an essential part of the treatment of prostate cancer and it is often difficult to predict its toxicity for the patients. Artificial intelligence could have a future potential role in predicting how a patient will react to the therapy side effects. These technologies could provide doctors with better insights on how to plan radiotherapy treatment. The extension of the capabilities of surgical robots for more autonomous tasks will allow them to use information from the surgical field, recognize issues and implement the proper actions without the need for human intervention.

Algorithms applied to spatially registered multi-parametric MRI for prostate tumor volume measurement

Background

Prostate tumor volume correlates with critical components of cancer staging such as Gleason score (GS) grade, predicted disease progression, and metastasis. Therefore, non-invasive tumor volume measurement may elevate clinical management. Radiology assessments of multi-parametric MRI (MP-MRI) commonly visually examine individual images to determine possible tumor presence. This study combines registered MP-MRI into a single image that display normal tissue and possible lesions. This study tests and exploits the vector nature of spatially registered MP-MRI by using supervised target detection algorithms (STDA) and color display and psychovisual analysis (CIELAB) to non-invasively estimate prostate tumor volume.

Methods

MRI, including T1, T2, diffusion [apparent diffusion coefficient (ADC)], dynamic contrast enhanced (DCE) images, were resampled, rescaled, translated, and stitched to form spatially registered Multi-parametric cubes. The multi-parametric or multi-spectral signatures (7-component or T1, T2, ADC, etc.) that characterize the prostate tumors were inserted into target detection algorithms with conical decision surfaces (adaptive cosine estimator, ACE). Various detection thresholds were applied to discriminate tumor from normal tissue. In addition, tumor appeared as yellow in color images that were created by assigning red to washout from DCE, green to high B from diffusion, and blue to autonomous diffusion image. The yellow voxels in the three-channel hypercube were visually identified by a reader and recording voxels that exceed a threshold in the b* component of the CIELAB algorithm. The number of reported tumor voxels were converted to volume based on spatial resolution and slice separation. The tumor volume measurements were quantitatively validated by comparing the tumor volume computations to the pathologist's assessment of the histology of sectioned whole mount prostates from 26 consecutive patients with prostate adenocarcinoma who underwent radical prostatectomy. This study analyzed tumors exceeding 1 cc and that also took up contrast material (18 patients).

Results

High correlation coefficients for tumor volume measurements using supervised target detection and color analysis vs. histology from wholemount prostatectomy were computed (R=0.83 and 0.91, respectively). A linear fit for tumor volume measurements using for supervised target detection and color analysis vs. tumor measurements from radical prostatectomy (after correcting for shrinkage from the radical prostatectomy) results in a slope of 1.02 and 3.02, respectively. A polynomial fit for the color analysis to the histology found (R=0.95). Voxels exceeding a threshold in the b* part of the CIELAB algorithm yielded correlation coefficients (0.71, 0.80) offsets (0.01 cc, -0.63 cc) and slopes (1.99, 0.89) against the wholemount prostatectomy and color analysis, respectively.

Conclusions

Supervised target detection and color display and analysis applied to registered MP-MRI non-invasively estimates prostate tumor volumes >1 cc and displaying angiogenesis.

Artificial intelligence in multiparametric prostate cancer imaging with focus on deep-learning methods

Prostate cancer represents today the most typical example of a pathology whose diagnosis requires multiparametric imaging, a strategy where multiple imaging techniques are combined to reach an acceptable diagnostic performance. However, the reviewing, weighing and coupling of multiple images not only places additional burden on the radiologist, it also complicates the reviewing process. Prostate cancer imaging has therefore been an important target for the development of computer-aided diagnostic (CAD) tools. In this survey, we discuss the advances in CAD for prostate cancer over the last decades with special attention to the deep-learning techniques that have been designed in the last few years. Moreover, we elaborate and compare the methods employed to deliver the CAD output to the operator for further medical decision making.