Multi-Stage Classification-Based Deep Learning for Gleason System Grading Using Histopathological Images.

In this work, we introduced an automated diagnostic system for Gleason system grading and grade groups (GG) classification using whole slide images (WSIs) of digitized prostate biopsy specimens (PBSs). Our system first classifies the Gleason pattern (GP) from PBSs and then identifies the Gleason score (GS) and GG. We developed a comprehensive DL-based approach to develop a grading pipeline system for the digitized PBSs and consider GP as a classification problem (not segmentation) compared to current research studies (deals with as a segmentation problem). A multilevel binary classification was implemented to enhance the segmentation accuracy for GP. Also, we created three levels of analysis (pyramidal levels) to extract different types of features. Each level has four shallow binary CNN to classify five GP labels. A majority fusion is applied for each pixel that has a total of 39 labeled images to create the final output for GP. The proposed framework is trained, validated, and tested on 3080 WSIs of PBS. The overall diagnostic accuracy for each CNN is evaluated using several metrics: precision (PR), recall (RE), and accuracy, which are documented by the confusion matrices.The results proved our system's potential for classifying all five GP and, thus, GG. The overall accuracy for the GG is evaluated using two metrics, PR and RE. The grade GG results are between 50% to 92% for RE and 50% to 92% for PR. Also, a comparison between our CNN architecture and the standard CNN (ResNet50) highlights our system's advantage. Finally, our deep-learning system achieved an agreement with the consensus grade groups.

Intralesional methotrexate versus triamcinolone acetonide for localized alopecia areata treatment: A randomized clinical trial.

BACKGROUND: Multiple therapeutic modalities are available for alopecia areata (AA) but still a challenging disease with variable severity, recurrence, and a major cosmetic concern. AIMS: Compare the effectiveness and safety of intralesional methotrexate (MTX) versus triamcinolone acetonide (TrA) in the treatment of localized AA in adults, both clinically and trichoscopically. PATIENTS/METHODS: 40 adult patients with localized AA were recruited and divided into two groups. 20 patients were treated by intralesional TrA and the other 20 patients were treated by intralesional MTX every 3 weeks, for maximum four sessions. Clinical and trichoscopic evaluation at baseline, each session and for 3 months after the last session was performed. RESULTS: At the end of sessions (12 weeks), regrowth scale was significantly higher in TrA group compared to MTX group (p-value = 0.028). But, after 3-month follow-up, regrowth scale was higher in MTX group compared to TrA group (p-value = 0.153). A statistically significant reduction in AA specific trichoscopic signs after 12 weeks and at the 3-month follow-up in both groups. Local adverse events in both groups were transient and disappeared during the follow-up period. CONCLUSION: Intralesional MTX in treatment of localized AA in adults can be promising and comparable to intralesional TrA with the need for further controlled and extensive trials. Trichoscopy can reveal early clinical response through disappearance of AA-specific trichoscopic signs and also early detection of adverse effects.

A Deep Learning Pipeline for Grade Groups Classification Using Digitized Prostate Biopsy Specimens.

Prostate cancer is a significant cause of morbidity and mortality in the USA. In this paper, we develop a computer-aided diagnostic (CAD) system for automated grade groups (GG) classification using digitized prostate biopsy specimens (PBSs). Our CAD system aims to firstly classify the Gleason pattern (GP), and then identifies the Gleason score (GS) and GG. The GP classification pipeline is based on a pyramidal deep learning system that utilizes three convolution neural networks (CNN) to produce both patch- and pixel-wise classifications. The analysis starts with sequential preprocessing steps that include a histogram equalization step to adjust intensity values, followed by a PBSs' edge enhancement. The digitized PBSs are then divided into overlapping patches with the three sizes: 100 × 100 (CNNS), 150 × 150 (CNNM), and 200 × 200 (CNNL), pixels, and 75% overlap. Those three sizes of patches represent the three pyramidal levels. This pyramidal technique allows us to extract rich information, such as that the larger patches give more global information, while the small patches provide local details. After that, the patch-wise technique assigns each overlapped patch a label as GP categories (1 to 5). Then, the majority voting is the core approach for getting the pixel-wise classification that is used to get a single label for each overlapped pixel. The results after applying those techniques are three images of the same size as the original, and each pixel has a single label. We utilized the majority voting technique again on those three images to obtain only one. The proposed framework is trained, validated, and tested on 608 whole slide images (WSIs) of the digitized PBSs. The overall diagnostic accuracy is evaluated using several metrics: precision, recall, F1-score, accuracy, macro-averaged, and weighted-averaged. The (CNNL) has the best accuracy results for patch classification among the three CNNs, and its classification accuracy is 0.76. The macro-averaged and weighted-average metrics are found to be around 0.70-0.77. For GG, our CAD results are about 80% for precision, and between 60% to 80% for recall and F1-score, respectively. Also, it is around 94% for accuracy and NPV. To highlight our CAD systems' results, we used the standard ResNet50 and VGG-16 to compare our CNN's patch-wise classification results. As well, we compared the GG's results with that of the previous work.

Impact of 18F-2-fluoro-2-deoxy-D-glucose PET/computerized tomography on the initial staging and changing the management intent in head and neck squamous cell carcinoma.

OBJECTIVE: To assess the role of 18F-FDG PET/CT in initial staging of head and neck squamous cell carcinoma and its impact on changing the management compared to other conventional methods. PATIENTS AND METHODS: A prospective study of 31 patients (21 male and 10 female), mean age 49.3 ± 12.1 years with histologically confirmed squamous cell carcinoma of the head and neck (nasopharynx was the commonest cancer in 15 patients (48.4%), poorly differentiated grade represented 64.5% of all tumors. Initial staging was achieved according to routine physical examination, endoscopy, CT, U/S, MRI. RESULTS: The overall change in TNM staging by 18F-FDG PET/CT in relation to conventional methods was encountered in 15/31 patients (48.4%). PET/CT changed; T staging in three patients (9.6%), upstaging in two patients and downstaging in one patient. PET/CT upstaged all 13/31 patients in N staging (41.9%). 18F-FDG PET/CT changed; M staging in 3/31 (9.6%) patients, upstaging in two and downstaging in one patient. PET/CT results caused radiotherapy modification in 21/31 patients (67.7%). PET/CT detected intra-parotid nodule in four patients, so additional radiation was added to the parotid in the treatment field. Retropharyngeal nodes were detected by PET/CT in three patients that were missed by conventional imaging. 18F-FDG PET/CT detected two patients of thyroid papillary carcinoma and one case of sigmoid neoplasm confirmed by histopathology. CONCLUSION: 18F-FDG-PET/CT is considered a valuable diagnostic test in head and neck squamous cell carcinoma at initial assessment which would change staging and radiotherapy planning and hence proper management.

Combined treatment with fractional carbon dioxide laser, autologous platelet-rich plasma, and narrow band ultraviolet B for vitiligo in different body sites: A prospective, randomized comparative trial.

BACKGROUND: Multiple treatment options are introduced in treatment of vitiligo but the response is unsatisfactory. OBJECTIVE: In this prospective, randomized, comparative trial, we studied the effect of combined treatment with fractional carbon dioxide (CO2 ) laser, platelet-rich plasma (PRP) injection, and narrowband ultraviolet B (NB-UVB) for stable nonsegmental vitiligo regarding repigmentation grade, patient's satisfaction, and side effects. METHODS: Eighty adult patients with localized nonsegmental vitiligo were enrolled in this study. The patients were randomly categorized to receive 4 lines of treatment; fractional CO2 laser, PRP, combined fractional CO2 laser and PRP, and combined fractional CO2 laser and NB-UVB. The treatment period was 2 months. Patients were clinically evaluated 3 months after the last treatment. Outcome was evaluated by 5-point scale for repigmentation, 10-point visual analog scale for patient's satisfaction, and side effects. RESULTS: Laser and PRP group achieved the best results regarding repigmentation and patient's satisfaction. Sixty percent of the patients developed repigmentation >50% and 40% of patients developed repigmentation >75%. In laser and NB-UVB group, 5% developed repigmentation >75% and 25% developed repigmentation >50%. Only 10% of patients developed repigmentation >75% in laser group and only 20% of patients developed repigmentation >75% in PRP group. CONCLUSIONS: Combination of fractional CO2 laser with PRP injection is a promising treatment for vitiligo, followed by combination of fractional CO2 laser with NB-UVB phototherapy. Both fractional CO2 laser and PRP injection gave poor results if they received alone.