Index tumor location affected early biochemical recurrence after radical prostatectomy in patients with negative surgical margin: a retrospective study.

BACKGROUND: Index tumors are the most aggressive tumors of the prostate. However, their clinical significance remains unclear. This study aimed to assess the incidence of index tumor location according to the zonal origin and whether these locations affect the prognosis after radical prostatectomy in patients with negative surgical margins. METHODS: This single-centered, retrospective study evaluated 1,109 consecutive patients who underwent radical prostatectomies. An index tumor was defined as the largest tumor in the prostate gland. We detected these locations based on McNeal's zonal origin using whole-mount sections. Biochemical recurrence (BCR) free survival curves were generated using the Kaplan-Meier method. Univariate and multivariate analyses using the Cox proportional hazards model were performed to determine the predictive factors for early BCR (within 1-year). RESULTS: A total of 621 patients with negative surgical margins who did not receive adjuvant therapy were included in this study. The index tumor were located in the transitional zone in 191 patients (30.8%), the peripheral zone in 399 patients (64.3%), and the central zone in 31 patients (5.0%). In total, 22 of 621 patients (3.5%) experienced early BCR and 70 patients (11.2%) experienced overall BCR at a median follow-up of 61.7 months. According to the index tumor location, the early BCR-free rates were 99.5%, 95.7 %, and 83.3% in the transitional, peripheral, and central zones, respectively. On multivariate analysis, the index tumor in the central zone was an independent predictor of early BCR with negative surgical margins following radical prostatectomy, followed by prostatectomy pathological grade, index tumor in the peripheral zone, and high prostate-specific antigen level. CONCLUSIONS: We assessed the significance of index tumor location in patients with negative surgical margins following radical prostatectomy. Index tumors located in the central zone, although infrequent, were the strongest predictive factors for early BCR. Our results may allow urologists and patients to reconsider the therapeutic strategies for prostate cancer.

Machine Learning of Histopathological Images Predicts Recurrences of Resected Pancreatic Ductal Adenocarcinoma With Adjuvant Treatment.

OBJECTIVES: Pancreatic ductal adenocarcinoma is an intractable disease with frequent recurrence after resection and adjuvant therapy. The present study aimed to clarify whether artificial intelligence-assisted analysis of histopathological images can predict recurrence in patients with pancreatic ductal adenocarcinoma who underwent resection and adjuvant chemotherapy with tegafur/5-chloro-2,4-dihydroxypyridine/potassium oxonate. MATERIALS AND METHODS: Eighty-nine patients were enrolled in the study. Machine-learning algorithms were applied to 10-billion-scale pixel data of whole-slide histopathological images to generate key features using multiple deep autoencoders. Areas under the curve were calculated from receiver operating characteristic curves using a support vector machine with key features alone and by combining with clinical data (age and carbohydrate antigen 19-9 and carcinoembryonic antigen levels) for predicting recurrence. Supervised learning with pathological annotations was conducted to determine the significant features for predicting recurrence. RESULTS: Areas under the curves obtained were 0.73 (95% confidence interval, 0.59-0.87) by the histopathological data analysis and 0.84 (95% confidence interval, 0.73-0.94) by the combinatorial analysis of histopathological data and clinical data. Supervised learning model demonstrated that poor tumor differentiation was significantly associated with recurrence. CONCLUSIONS: Results indicate that machine learning with the integration of artificial intelligence-driven evaluation of histopathological images and conventional clinical data provides relevant prognostic information for patients with pancreatic ductal adenocarcinoma.

Development of a prognostic prediction support system for cervical intraepithelial neoplasia using artificial intelligence-based diagnosis.

OBJECTIVE: Human papillomavirus subtypes are predictive indicators of cervical intraepithelial neoplasia (CIN) progression. While colposcopy is also an essential part of cervical cancer prevention, its accuracy and reproducibility are limited because of subjective evaluation. This study aimed to develop an artificial intelligence (AI) algorithm that can accurately detect the optimal lesion associated with prognosis using colposcopic images of CIN2 patients by utilizing objective AI diagnosis. METHODS: We identified colposcopic findings associated with the prognosis of patients with CIN2. We developed a convolutional neural network that can automatically detect the rate of high-grade lesions in the uterovaginal area in 12 segments. We finally evaluated the detection accuracy of our AI algorithm compared with the scores by multiple gynecologic oncologists. RESULTS: High-grade lesion occupancy in the uterovaginal area detected by senior colposcopists was significantly correlated with the prognosis of patients with CIN2. The detection rate for high-grade lesions in 12 segments of the uterovaginal area by the AI system was 62.1% for recall, and the overall correct response rate was 89.7%. Moreover, the percentage of high-grade lesions detected by the AI system was significantly correlated with the rate detected by multiple gynecologic senior oncologists (r=0.61). CONCLUSION: Our novel AI algorithm can accurately determine high-grade lesions associated with prognosis on colposcopic images, and these results provide an insight into the additional utility of colposcopy for the management of patients with CIN2.

A data-driven ultrasound approach discriminates pathological high grade prostate cancer.

Accurate prostate cancer screening is imperative for reducing the risk of cancer death. Ultrasound imaging, although easy, tends to have low resolution and high inter-observer variability. Here, we show that our integrated machine learning approach enabled the detection of pathological high-grade cancer by the ultrasound procedure. Our study included 772 consecutive patients and 2899 prostate ultrasound images obtained at the Nippon Medical School Hospital. We applied machine learning analyses using ultrasound imaging data and clinical data to detect high-grade prostate cancer. The area under the curve (AUC) using clinical data was 0.691. On the other hand, the AUC when using clinical data and ultrasound imaging data was 0.835 (p = 0.007). Our data-driven ultrasound approach offers an efficient tool to triage patients with high-grade prostate cancers and expands the possibility of ultrasound imaging for the prostate cancer detection pathway.

Automated acquisition of explainable knowledge from unannotated histopathology images.

Deep learning algorithms have been successfully used in medical image classification. In the next stage, the technology of acquiring explainable knowledge from medical images is highly desired. Here we show that deep learning algorithm enables automated acquisition of explainable features from diagnostic annotation-free histopathology images. We compare the prediction accuracy of prostate cancer recurrence using our algorithm-generated features with that of diagnosis by expert pathologists using established criteria on 13,188 whole-mount pathology images consisting of over 86 billion image patches. Our method not only reveals findings established by humans but also features that have not been recognized, showing higher accuracy than human in prognostic prediction. Combining both our algorithm-generated features and human-established criteria predicts the recurrence more accurately than using either method alone. We confirm robustness of our method using external validation datasets including 2276 pathology images. This study opens up fields of machine learning analysis for discovering uncharted knowledge.

Illuminating Clues of Cancer Buried in Prostate MR Image: Deep Learning and Expert Approaches.

Deep learning algorithms have achieved great success in cancer image classification. However, it is imperative to understand the differences between the deep learning and human approaches. Using an explainable model, we aimed to compare the deep learning-focused regions of magnetic resonance (MR) images with cancerous locations identified by radiologists and pathologists. First, 307 prostate MR images were classified using a well-established deep neural network without locational information of cancers. Subsequently, we assessed whether the deep learning-focused regions overlapped the radiologist-identified targets. Furthermore, pathologists provided histopathological diagnoses on 896 pathological images, and we compared the deep learning-focused regions with the genuine cancer locations through 3D reconstruction of pathological images. The area under the curve (AUC) for MR images classification was sufficiently high (AUC = 0.90, 95% confidence interval 0.87-0.94). Deep learning-focused regions overlapped radiologist-identified targets by 70.5% and pathologist-identified cancer locations by 72.1%. Lymphocyte aggregation and dilated prostatic ducts were observed in non-cancerous regions focused by deep learning. Deep learning algorithms can achieve highly accurate image classification without necessarily identifying radiological targets or cancer locations. Deep learning may find clues that can help a clinical diagnosis even if the cancer is not visible.

An infant case of diffuse cerebrospinal lesions and cardiomyopathy caused by a BOLA3 mutation.

INTRODUCTION: Mitochondrial dysfunction results in a wide range of organ disorders through diverse genetic abnormalities. We herein present the detailed clinical course of an infant admitted for extensive, rapidly progressing white matter lesions and hypertrophic cardiomyopathy due to a BOLA3 gene mutation. CASE: A 6-month-old girl with no remarkable family or past medical history until 1 month prior presented with developmental regression and feeding impairment. Ultrasound cardiography and brain magnetic resonance imaging (MRI) respectively disclosed the presence of hypertrophic cardiomyopathy and symmetrical deep white matter lesions. She was transferred to our hospital at age 6 months. High lactate levels in her cerebrospinal fluid suggested mitochondrial dysfunction. Despite vitamin supplementation therapy followed by a ketogenic diet, the patient began exhibiting clusters of myoclonic seizures and respiratory failure. Brain and spinal cord MRI revealed rapid progression of the white matter lesions. She died at 10 months of age. Fibroblasts obtained pre-mortem displayed low mitochondrial respiratory chain complex I and II activity. A homozygous H96R (c. 287 A > G) mutation was identified in the BOLA3 gene. DISCUSSION: No reported case of a homozygous BOLA3 gene mutation has survived past 1 year of life. BOLA3 appears to play a critical role in the electron transport system and production of iron-sulfur clusters that are related to lipid metabolism and enzyme biosynthesis.

Histopathological findings of pregnancy-induced hypertension: histopathology of early-onset type reflects two-stage disorder theory.

The placental tissues of pregnancy-induced hypertension (PIH) patients exhibit multiple infarctions, acute atherosis, distal villous hypoplasia, and increased syncytial knots. However, these findings are not observed in all cases of PIH; thus, the significance of these changes in PIH is still unclear. We studied the frequency of histopathological changes of placental tissue in the subgroups of PIH, such as mild and severe PIH and early-onset (< 34 weeks) and late-onset (≥ 34 weeks) PIH. One hundred seven cases of PIH diagnosed at the Shinshu University Hospital, Matsumoto, Japan, between 2008 and 2014 were collected. PIH includes preeclampsia and gestational hypertension. The pathologic changes evaluated in the placenta were multiple infarctions, acute atherosis, distal villous hypoplasia, and increased syncytial knots. Placental tissues of patients with early-onset PIH demonstrated acute atherosis resulting from the incomplete remodeling of the spiral arteries and distal villous hypoplasia and increased syncytial knots reflecting placental hypoxia/ischemia much more frequently than those with late-onset PIH (all p < 0.001). The frequencies of multiple infarctions did not show a statistical difference between early-onset PIH and late-onset PIH. Moreover, there were no significant differences in the frequencies of histopathological features of placental tissue between mild PIH and severe PIH. Early-onset PIH exhibited histopathological changes of placental tissue consistent with the two-stage disorder theory more frequently than late-onset PIH. These findings support the idea that early-onset PIH and late-onset PIH are distinct entities or different extremes of the PIH spectrum.

Quantitative diagnosis of breast tumors by morphometric classification of microenvironmental myoepithelial cells using a machine learning approach.

Machine learning systems have recently received increased attention for their broad applications in several fields. In this study, we show for the first time that histological types of breast tumors can be classified using subtle morphological differences of microenvironmental myoepithelial cell nuclei without any direct information about neoplastic tumor cells. We quantitatively measured 11661 nuclei on the four histological types: normal cases, usual ductal hyperplasia and low/high grade ductal carcinoma in situ (DCIS). Using a machine learning system, we succeeded in classifying the four histological types with 90.9% accuracy. Electron microscopy observations suggested that the activity of typical myoepithelial cells in DCIS was lowered. Through these observations as well as meta-analytic database analyses, we developed a paracrine cross-talk-based biological mechanism of DCIS progressing to invasive cancer. Our observations support novel approaches in clinical computational diagnostics as well as in therapy development against progression.

A novel method for morphological pleomorphism and heterogeneity quantitative measurement: Named cell feature level co-occurrence matrix.

BACKGROUND: Recent developments in molecular pathology and genetic/epigenetic analysis of cancer tissue have resulted in a marked increase in objective and measurable data. In comparison, the traditional morphological analysis approach to pathology diagnosis, which can connect these molecular data and clinical diagnosis, is still mostly subjective. Even though the advent and popularization of digital pathology has provided a boost to computer-aided diagnosis, some important pathological concepts still remain largely non-quantitative and their associated data measurements depend on the pathologist's sense and experience. Such features include pleomorphism and heterogeneity. METHODS AND RESULTS: In this paper, we propose a method for the objective measurement of pleomorphism and heterogeneity, using the cell-level co-occurrence matrix. Our method is based on the widely used Gray-level co-occurrence matrix (GLCM), where relations between neighboring pixel intensity levels are captured into a co-occurrence matrix, followed by the application of analysis functions such as Haralick features. In the pathological tissue image, through image processing techniques, each nucleus can be measured and each nucleus has its own measureable features like nucleus size, roundness, contour length, intra-nucleus texture data (GLCM is one of the methods). In GLCM each nucleus in the tissue image corresponds to one pixel. In this approach the most important point is how to define the neighborhood of each nucleus. We define three types of neighborhoods of a nucleus, then create the co-occurrence matrix and apply Haralick feature functions. In each image pleomorphism and heterogeneity are then determined quantitatively. For our method, one pixel corresponds to one nucleus feature, and we therefore named our method Cell Feature Level Co-occurrence Matrix (CFLCM). We tested this method for several nucleus features. CONCLUSION: CFLCM is showed as a useful quantitative method for pleomorphism and heterogeneity on histopathological image analysis.

Tumour and immune cell dynamics explain the PSA bounce after prostate cancer brachytherapy.

BACKGROUND: Interstitial brachytherapy for localised prostate cancer may be followed by transient increases in prostate-specific antigen (PSA) that resolve without therapy. Such PSA bounces may be associated with an improved outcome but often cause alarm in the patient and physician, and have defied explanation. METHODS: We developed a mathematical model to capture the interactions between the tumour, radiation and anti-tumour immune response. The model was fitted to data from a large cohort of patients treated exclusively with interstitial brachytherapy. Immunohistological analysis for T-cell infiltration within the same tumours was also performed. RESULTS: Our minimal model captures well the dynamics of the tumour after therapy, and suggests that a strong anti-tumour immune response coupled with the therapeutic effect of radiation on the tumour is responsible for the PSA bounce. Patients who experience a PSA bounce had a higher density of CD3 and CD8 cells within the tumour that likely contribute to the PSA bounce and the overall better outcomes observed. CONCLUSIONS: Our observations provide a novel and unifying explanation for the PSA bounce in patients with early prostate cancer and also have implications for the use of immune-based therapies in such patients to improve outcomes.

Quantitative nucleic features are effective for discrimination of intraductal proliferative lesions of the breast.

BACKGROUND: Intraductal proliferative lesions (IDPLs) of the breast are recognized as a risk factor for subsequent invasive carcinoma development. Although opportunities for IDPL diagnosis have increased, these lesions are difficult to diagnose correctly, especially atypical ductal hyperplasia (ADH) and low-grade ductal carcinoma in situ (LG-DCIS). In order to define the difference between these lesions, many molecular pathological approaches have been performed. However, still we do not have a molecular marker and objective histological index about IDPLs of the breast. METHODS: We generated full digital pathology archives from 175 female IDPL patients, including usual ductal hyperplasia (UDH), ADH, LG-DCIS, intermediate-grade (IM)-DCIS, and high-grade (HG)-DCIS. After total 2,035,807 nucleic segmentations were extracted, we evaluated nuclear features using step-wise linear discriminant analysis (LDA) and a support vector machine. RESULTS: High diagnostic accuracy (81.8-99.3%) was achieved between pathologists' diagnoses and two-group LDA predictions from nucleic features for IDPL discrimination. Grouping of nuclear features as size and shape-related or intranuclear texture-related revealed that the latter group was more important when distinguishing between normal duct, UDH, ADH, and LG-DCIS. However, these two groups were equally important when discriminating between LG-DCIS and HG-DCIS. The Mahalanobis distances between each group showed that the smallest distance values occurred between LG-DCIS and IM-DCIS and between ADH and Normal. On the other hand, the distance value between ADH and LG-DCIS was larger than this distance. CONCLUSIONS: In this study, we have presented a practical and useful digital pathological method that incorporates nuclear morphological and textural features for IDPL prediction. We expect that this novel algorithm is used for the automated diagnosis assisting system for breast cancer.

Quantitative analysis of nuclear shape in oral squamous cell carcinoma is useful for predicting the chemotherapeutic response.

The number of people afflicted with oral carcinoma in Japan has increased in recent years. Although preoperative neoadjuvant therapy with cisplatin and 5-fluorouracil are performed, chemotherapeutic response varies widely among the patients. With the aim of establishing novel indices to predict the therapeutic response to chemotherapy, we investigated the relationship between morphological features of pre-treatment oral carcinoma nuclei and the chemotherapeutic response using quantifying morphology of cell nuclei in pathological specimen images. We measured 4 morphological features of the nucleus of oral squamous cell carcinoma cases classified by the response to chemotherapy: No Change (NC) group, Partial Response (PR) group and Complete Response (CR) group. Furthermore, we performed immunohistochemical staining for p53 and Ki67 and calculated their positive rates in cancer tissues. Compactness and symmetry of the nucleus were significantly higher and nuclear edge response was significantly lower in cancer cells with lower chemotherapeutic responses compared high chemotherapeutic responders. As for positive rates of p53 and Ki67, there were no significant differences between any of the response groups. Morphological features of cancer cell nuclei in pathological specimens are sensitive predictive factors for the chemotherapeutic response to oral squamous cell carcinoma.

Inferior vena cava tumor thrombus after partial nephrectomy for renal cell carcinoma.

BACKGROUND: Partial nephrectomy is now the gold standard treatment for small renal tumors. Local recurrence is a major problem after partial nephrectomy, and local recurrence in the remnant kidney after partial nephrectomy is common. CASE PRESENTATION: A 77-year-old man underwent right partial nephrectomy for a T1 right renal cell carcinoma. Microscopic examination revealed a clear cell renal carcinoma, grade 2, stage pT3a. Although the surgical margin was negative, the carcinoma invaded the perirenal fat, and vascular involvement was strongly positive. Thirty months after partial nephrectomy, an enhanced computed tomographic scan showed local recurrence of the renal cell carcinoma extending into the inferior vena cava without renal mass. Hence, we performed right radical nephrectomy and intracaval thrombectomy. Microscopic examination revealed a clear cell carcinoma grade 2, stage pT3a + b. The patient is still alive with no evidence of recurrence 10 months post-procedure. CONCLUSION: To our knowledge, local recurrence of renal cell carcinoma extending into the inferior vena cava after partial nephrectomy has not been reported in the literature. Our case report emphasizes the importance of strict surveillance of patients after partial nephrectomy, especially for those with renal cell carcinoma positive for microvessel involvement.

Supratentorial extraventricular anaplastic ependymoma in an adult with repeated intratumoral hemorrhage.

We report the case of a 61-year-old man with supratentorial extraventricular anaplastic ependymoma who presented with repeated intratumoral hemorrhage. The patient was admitted with headache. Computed tomography and magnetic resonance imaging showed an enhancing mass with intratumoral hemorrhage in the right temporal lobe. Gross total resection was performed. The tumor was well demarcated from the brain tissue, and showed no continuity with the ventricular system. Histopathological examination revealed the features of anaplastic ependymoma. Therefore, additional radiation therapy and adjuvant chemotherapy were administered. Ten months later, the tumor recurred with hemorrhage in the spinal canal. This case showed rapid malignant progression and repeated intratumoral hemorrhage within a short period of time, both of which are characteristics of anaplastic ependymomas. Close observation of the central nervous system and adjuvant radiotherapy are mandatory, even if the ependymoma presents with repeated intratumoral hemorrhage.

Age-related decrease of the retinal vasculature area identified with a novel computer-aided analysis system.

Fundus photographs enable non-invasive analysis of the status of the microcirculation by directly observing the retinal vasculature. Retinal microvascular abnormalities are important clinical markers of hypertension and arteriosclerosis, but retinal microvascular changes can be observed in older individuals without hypertension. In this study, our goal is to elucidate the effects of aging on fundus vessels in the retinal photograph. We analyzed retinal vessels of 161 healthy volunteers (49.5 ± 18.7 years, range 18-87) using in-house computer-aided measurement system to measure areas and diameters of all retinal vessels across the entire area of a retinal photograph. The vessels were segmented according to color, and then their area, size, length and thickness were measured by image processing. We also analyzed the correlation between total blood vessel area, age and mean arterial blood pressure (MABP). The decrease in total blood vessel area was dependent on both age and MABP. Moreover, decrease in blood vessel area was also correlated with age for the normotensive group. Furthermore, the slope of the regression line for retinal vessel area with MABP was significantly higher in participants aged ≤ 60 years than in those aged over 60 years. Changes in retinal vessel area with aging were observed in both arterioles and venules. In conclusion, we found the significant decrease in retinal vessel area that is correlated well with calendar age. Therefore, we need to carefully apply traditional classifications of fundus examination for hypertensive retinopathy in older individuals.

[A case of late recurrence of urothelial carcinoma in an ileal conduit after radical cystectomy and ileal conduit diversion for bladder cancer].

Recurrence of urothelial cancer in an ileal conduit after radical cystectomy is rare. A 79-year-old man suffered bladder cancer (UC cTisN0M0 G2＞3) and underwent total cystectomy with ileal conduit. He had recurrence of the right renal pelvis carcinoma 6 years after the total cystectomy, and was treated by right radical nephroureterectomy (pT3 G2＝3). The patient had another episode of recurrence in the ileal conduit 13 years after the initial operation. The entire ileal conduit (UC, G3, ew (-)) was resected and left cutaneous ureterostomy was performed. This case suggests that long-term follow-up is necessary after radical cystectomy and ileal conduit for urinary diversion.

Roles of fine-needle aspiration and core needle biopsy in the diagnosis of breast cancer.

BACKGROUND: There is controversy regarding which of the two biopsy methods, fine-needle aspiration (FNA) or core needle biopsy (CNB), should be routinely employed for diagnosis of breast cancer. The aim of this study was to evaluate the efficacy of FNA compared to CNB and to explore the value of performing both FNA and CNB. METHODS: Two hundred eighty-one patients with breast cancer received FNA alone (group 1: n = 182), CNB alone (group 2: n = 56), or a combination of FNA and CNB (group 3: n = 43). In group 3, FNA was combined with CNB because of an inadequate smear of FNA on immediate cytological examination. Subsequently, the patients underwent definitive surgery or open surgical biopsy based on the clinical findings, and the tumors were pathologically confirmed to be noninvasive or invasive breast cancer. RESULTS: There was no significant difference in the absolute sensitivity between group 1 (93% for FNA alone) and group 2 (86% for CNB alone). In group 3, on the other hand, the absolute sensitivity was significantly improved to 72% when FNA and CNB were combined (P < 0.05), although it was only 42% for FNA alone and 63% for CNB alone. CONCLUSIONS: The absolute sensitivity of FNA was equivalent to that of CNB when excluding patients who were converted from FNA to CNB based on immediate cytological examination. In the latter patients, however, it was improved by combining FNA and CNB. Therefore, these two techniques should be considered complimentary to one another.