Machine learning applied to MRI evaluation for the detection of lymph node metastasis in patients with locally advanced cervical cancer treated with neoadjuvant chemotherapy.

PURPOSE: Concurrent cisplatin-based chemotherapy and radiotherapy (CCRT) plus brachytherapy is the standard treatment for locally advanced cervical cancer (LACC). Platinum-based neoadjuvant chemotherapy (NACT) followed by radical hysterectomy is an alternative for patients with stage IB2-IIB disease. Therefore, the correct pre-treatment staging is essential to the proper management of this disease. Pelvic magnetic resonance imaging (MRI) is the gold standard examination but studies about MRI accuracy in the detection of lymph node metastasis (LNM) in LACC patients show conflicting data. Machine learning (ML) is emerging as a promising tool for unraveling complex non-linear relationships between patient attributes that cannot be solved by traditional statistical methods. Here we investigated whether ML might improve the accuracy of MRI in the detection of LNM in LACC patients. METHODS: We analyzed retrospectively LACC patients who underwent NACT and radical hysterectomy from 2015 to 2020. Demographic, clinical and MRI characteristics before and after NACT were collected, as well as information about post-surgery histopathology. Random features elimination wrapper was used to determine an attribute core set. A ML algorithm, namely Extreme Gradient Boosting (XGBoost) was trained and validated with tenfold cross-validation. The performances of the algorithm were assessed. RESULTS: Our analysis included n.92 patients. FIGO stage was IB2 in n.4/92 (4.3%), IB3 in n.42/92 (45%), IIA1 in n.1/92 (1.1%), IIA2 in n.16/92 (17.4%) and IIB in n.29/92 (31.5%). Despite detected neither at pre-treatment and post-treatment MRI in any patients, LNM occurred in n.16/92 (17%) patients. The attribute core set used to train ML algorithms included grading, histotypes, age, parity, largest diameter of lesion at either pre- and post-treatment MRI, presence/absence of fornix infiltration at pre-treatment MRI and FIGO stage. XGBoost showed a good performance (accuracy 89%, precision 83%, recall 78%, AUROC 0.79). CONCLUSIONS: We developed an accurate model to predict LNM in LACC patients in NACT, based on a ML algorithm requiring few easy-to-collect attributes.

A machine learning approach applied to gynecological ultrasound to predict progression-free survival in ovarian cancer patients.

In a growing number of social and clinical scenarios, machine learning (ML) is emerging as a promising tool for implementing complex multi-parametric decision-making algorithms. Regarding ovarian cancer (OC), despite the standardization of features that can support the discrimination of ovarian masses into benign and malignant, there is a lack of accurate predictive modeling based on ultrasound (US) examination for progression-free survival (PFS). This retrospective observational study analyzed patients with epithelial ovarian cancer (EOC) who were followed in a tertiary center from 2018 to 2019. Demographic features, clinical characteristics, information about the surgery and post-surgery histopathology were collected. Additionally, we recorded data about US examinations according to the International Ovarian Tumor Analysis (IOTA) classification. Our study aimed to realize a tool to predict 12 month PFS in patients with OC based on a ML algorithm applied to gynecological ultrasound assessment. Proper feature selection was used to determine an attribute core set. Three different machine learning algorithms, namely Logistic Regression (LR), Random Forest (RFF), and K-nearest neighbors (KNN), were then trained and validated with five-fold cross-validation to predict 12 month PFS. Our analysis included n. 64 patients and 12 month PFS was achieved by 46/64 patients (71.9%). The attribute core set used to train machine learning algorithms included age, menopause, CA-125 value, histotype, FIGO stage and US characteristics, such as major lesion diameter, side, echogenicity, color score, major solid component diameter, presence of carcinosis. RFF showed the best performance (accuracy 93.7%, precision 90%, recall 90%, area under receiver operating characteristic curve (AUROC) 0.92). We developed an accurate ML model to predict 12 month PFS.

Micro-computed tomography of isolated fetal hearts following termination of pregnancy: A feasibility study at 8 to 12 weeks' gestation.

OBJECTIVES: To assess the feasibility of retrieval of intact human fetal hearts after first trimester surgical termination of pregnancy (TOP) and subsequent anatomical assessment by postmortem micro-computed tomography (micro-CT). METHODS: In a cohort of consenting women undergoing surgical TOP between 8 and 13 weeks' gestation, we attempted the retrieval of the fetal heart from the suction material. Specimens were immersion fixed in 10% formaldehyde, scanned by iodine-enhanced micro-CT and cardiac anatomy assessed by a multidisciplinary team using 3D-multiplanar analysis. RESULTS: The median gestational age at TOP was 10.7 weeks (range 8.3-12.9). In 57 (95.0%) out of 60 suction specimens, the heart could be retrieved. The median cardiac length was 5 mm (range 2-8 mm), in three (5.3%), the heart was too damaged to assess cardiac anatomy and in five (8.7%) only the four chambers could be examined. In the remaining 49 (86.0%) cases, a detailed assessment of cardiac anatomy was possible, showing a major defect in two (4.1%) and a minor defect in four (8.2%). CONCLUSIONS: Fetal hearts can be retrieved after first trimester TOP being intact in the vast majority of cases. Iodine-enhanced, postmortem micro-CT can be used to assess cardiac anatomy from as early as 8 weeks and to describe heart abnormalities.

Micro-computed tomography: a new diagnostic tool in postmortem assessment of brain anatomy in small fetuses.

PURPOSE: The aim of our study was to evaluate the postmortem micro-CT anatomy of early fetal human fetal brains, either in situ or isolated. METHODS: We studied 12 ex vivo specimens, 9 whole human fetuses (9-18 GW), and 3 isolated samples (16-26 GW). Specimens were fixed in formalin, then immersed in Lugol solution. Images were evaluated by two neuroradiologists. The depiction of CNS structures was defined based on the comparison between micro-CT images and a reference histologic anatomical Atlas of human brain development. RESULTS: Micro-CT provided informative high-resolution brain images in all cases, with the exception of one case (9 weeks) due to advanced maceration. All major CNS structures (i.e., brain hemispheres, layering, ventricles, germinal neuroepithelium, basal ganglia, corpus callosum, major cranial nerves, and structures of the head and neck) were recognizable. CONCLUSIONS: Micro-CT imaging of the early fetal brain is feasible and provides high-quality images that correlate with the histological Atlas of the human brain, offering multiplanar and volumetric images that can be stored and shared for clinical, teaching, and research purposes.

Effects of Simvastatin on Fetal Cardiac Impairment in the Diaphragmatic Experimental Hernia Model.

BACKGROUND: Statins and sildenafil have been shown to exert beneficial effects in cardiac injury. We hypothesized that antenatal maternal administration of simvastatin and/or sildenafil might also promote benefits in cardiac remodeling of congenital diaphragmatic hernia (CDH). Therefore, we performed micro-CT image analysis and histology of the heart after antennal treatment in experimental nitrofen-induced CDH. METHODS: At 9.5 days post conception (dpc), pregnant rats were exposed to nitrofen. At 16 and 20 dpc fetuses were treated with simvastatin and/or sildenafil. At 21 dpc postmortem micro-CT and autopsy were performed. RESULTS: All nitrofen-treated fetuses had a lower birth weight compared to controls; in the simvastatin-treated group, a significant improvement in CDH was noted. Impairment of the lung and liver was also noted in CDH. Compared to controls, CDH rats showed lower ventricular mass, with greater left ventricular thickness; simvastatin decreased the ventricular mass and improved wall thickness. CDH rats exhibited myocardial hypotrophy, severe vascular depression in the left ventricle, and intense interstitial edema compared to controls and nitrofen-exposed animals without CDH. In CDH, the cardiac morphology appeared deformed with left ventricular wall verticalization. Simvastatin improved cardiac myocyte appearance and heart morphology. CONCLUSION: The potential to treat CDH with antenatal simvastatin may improve the management of this malformation.

Postmortem microfocus computed tomography for early gestation fetuses: a validation study against conventional autopsy.

BACKGROUND: Perinatal autopsy provides useful clinical information in up to 40% of cases. However, there is a substantial unmet clinical need with regards to postmortem investigation of early gestation fetal loss for parents for whom standard autopsy is either not available or not acceptable. Parents dislike the invasive nature of autopsy, but current clinical imaging techniques do not provide high-enough imaging resolution in small fetuses. We hypothesized that microfocus computed tomography, which is a rapid high-resolution imaging technique, could give accurate diagnostic imaging after early gestation fetal loss. OBJECTIVE: The objective of the study was to evaluate the diagnostic accuracy of microfocus computed tomography for noninvasive human fetal autopsy for early gestation fetuses, with the use of conventional autopsy as the reference standard. STUDY DESIGN: We compared iodinated whole body microfocus computed tomography in 20 prospectively recruited fetuses (11-21 weeks gestation from 2 centers) with conventional autopsy in a double-blinded manner for a main diagnosis and findings in specific body organs. Fetuses were prepared with 10% formalin/potassium tri-iodide. Images were acquired with a microfocus computed tomography scanner with size-appropriate parameters. Images were evaluated independently by 2 pediatric radiologists, who were blinded to formal perinatal autopsy results, across 40 individual indices to reach consensus. The primary outcome was agreement between microfocus computed tomography and conventional autopsy for overall diagnosis. RESULTS: Postmortem whole body fetal microfocus computed tomography gave noninvasive autopsy in minutes, at a mean resolution of 27µm, with high diagnostic accuracy in fetuses at <22 weeks gestation. Autopsy demonstrated that 13 of 20 fetuses had structural abnormalities, 12 of which were also identified by microfocus computed tomography (92.3%). Overall, microfocus computed tomography agreed with overall autopsy findings in 35 of 38 diagnoses (15 true positive, 18 true negative; sensitivity 93.8% [95% confidence interval, 71.7-98.9%], specificity 100% [95% confidence interval, 82.4-100%]), with 100% agreement for body imaging diagnoses. Furthermore, after removal of nondiagnostic indices, there was agreement for 700 of 718 individual body organ indices that were assessed on microfocus computed tomography and autopsy (agreement, 97.5%; 95% confidence interval, 96.1-98.4%), with no overall differences between fetuses at ≤14 or >14 weeks gestation (agreement, 97.2% and 97.9%, respectively). Within first-trimester fetal loss cases (<14 weeks gestation), microfocus computed tomography analysis yielded significantly fewer nondiagnostic indices than autopsy examination (22/440 vs 48/348, respectively; P<.001). CONCLUSION: Postmortem whole-body fetal microfocus computed tomography gives noninvasive, detailed anatomic examinations that are achieved in minutes at high resolution. Microfocus computed tomography may be preferable to magnetic resonance imaging in early gestation fetuses and may offer an acceptable method of examination after fetal loss for parents who decline invasive autopsy. This will facilitate autopsy and subsequent discussions between medical professionals who are involved in patient care and counselling for future pregnancies.

Fetal Cardiac Impairment in Nitrofen-Induced Congenital Diaphragmatic Hernia: Postmortem Microcomputed Tomography Imaging Study.

INTRODUCTION: We assessed the post-mortem micro-CT utility to evaluate fetal cardiac impairment in nitrofen-induced congenital diaphragmatic hernia (CDH). METHODS: At 9.5d postconception (dpc), pregnant rats were exposed to nitrofen. At +18 and +21dpc, fetuses were harvested by cesarean section. Postmortem micro-CT and autopsy were performed. Fetuses were assigned to three experimental groups: Control group (C), Nitrofen group (N, exposition to nitrofen without CDH), CDH group. Cardio-pulmonary indices were evaluated. RESULTS: An accurate morphological evaluation of the lung and heart was obtained. Early cardiac impairment was present in the N and CDH groups. At term pregnancy, an increased maximum diameter and decreased minimum diameter of the ventricles and increased interventricular septal thickness were noted in CDH. Histology showed a myocardial "disarray" and an high density of mitotic myocytes in CDH at midgestation. CONCLUSIONS: The potential utility of post-mortem fetal micro-CT examination in CDH was introduced. The results highlighted the presence of cardiac adaptation in affected fetuses.

Performance, nitrogen balance and microbial efficiency of beef cattle under concentrate supplementation strategies in intensive management of a tropical pasture.

The objective of this study was to evaluate the effect of concentrate supplementation strategies on the nutritional characteristics of beef cattle in intensive management of tropical pasture. Twenty-four Nellore steer at 250 kg body weight (BW) were used, divided into two plots, with 12 animals in each plot. The experimental area consisted of 32 paddocks with 0.25 ha of Panicum maximum cv. Mombaça. The experiment consisted of 96-day experimental periods, with three periods of 32 days. The strategies studied were P = exclusively on pasture and without concentrate supplementation (control), ES = pasture and supplemented with a concentrate low in protein, PS = pasture and supplemented with high protein content, and PES = pasture and supplementation with balanced protein-energy. There was reduced intake of DM in animals of the treatment P in relation to supplemented pasture, regardless of supplementation. Animals fed on ES showed an intake of more nutrients than the animals on PS. The CP and TDN were also lower in P than in pastures where animals received the additional types of concentrate, and the PS animals showed greater digestibility of CP and TDN than the ES animals. However, the animals exhibited similar weight gains. Animals on P ingested smaller amounts of N and had lower fecal excretion compared to the supplemented animals, but there was no difference between treatments in nitrogen balance. Urea nitrogen and urea from the blood were higher in the supplemented animals than in animals fed on pasture; these levels were also higher in PS animals compared to animals receiving ES. Both the purines absorbed and microbial protein production were similar between treatments. However, the animals fed with concentrate supplementation, independent of the strategy involved, showed higher microbial efficiency compared to animals fed exclusively on pasture.

Overlap of Suspicious and Non-Suspicious Features in the Ultrasound Evaluations of Leiomyosarcoma: A Single-Center Experience.

Leiomyosarcoma (LMS) is a rare type of mesenchymal tumor. Suspecting LMS before surgery is crucial for proper patient management. Ultrasound is the primary method for assessing myometrial lesions. The overlapping of clinical, laboratory, as well as ultrasound features between fibroids and LMS makes differential diagnosis difficult. We report our single-center experience in ultrasound imaging assessment of LMS patients, highlighting that misleading findings such as shadowing and absent or minimal vascularization may also occur in LMS. To avoid mistakes, a comprehensive evaluation of potentially overlapping ultrasound features is necessary in preoperative ultrasound evaluations of all myometrial tumors.

Preoperative sonographic assessment of a leiomyoma of the round ligament.

NA.

The Application of Sonovaginography for Implementing Ultrasound Assessment of Endometriosis and Other Gynaecological Diseases.

Sonovaginography is a way of assessing gynaecological diseases that can be described as cheap yet accurate and non-invasive. It consists of distention of the vagina with ultrasound gel or saline solution while performing transvaginal sonography to clearly visualize and assess a host of local cervical, as well as any vaginal, disorders. With endometriosis being a steadily growing gynaecological pathology affecting 8-15% of women of fertile age, transvaginal sonography (TVS) can be considered as one of the most accurate and comprehensive imaging techniques in its diagnosis. Nevertheless, the accuracy may vary depending on scan sites. The purpose of this narrative review is to assess the performance of sonovaginography in detecting endometriosis in those sites where TVS has a low sensitivity.

Postmortem Micro-CT of Human Fetal Heart-A Systematic Literature Review.

Micro-computed tomography (CT) is a non-invasive alternative to conventional macroscopic dissection for the evaluation of human fetal cardiac anatomy. This paper aims to systematically review the literature regarding the use of micro-CT to examine human fetal hearts, to illustrate its educational and research implications and to explain its possible directions for the future. A systematic literature review was conducted following the PRISMA statement to identify publications concerning micro-CT applications for the isolated human fetal heart. The search strategy identified nine eligible studies. Micro-CT is technically feasible for postmortem examination of the human fetal heart coming from early and late termination of pregnancy. It reaches high diagnostic accuracy, and it seems to perform better than autopsy in small samples or in the case of early termination of pregnancy. Applications derived from micro-CT allow multiple off-time evaluations and interdisciplinary comparisons for educational purposes and research perspectives in biological and bioengineering domains.

HPV-Negative Cervical Cancer: A Narrative Review.

Cervical cancer (CC) is the fourth most frequent cancer in women worldwide. HPV infection is associated with the majority of CC cases, but a small proportion of CCs actually test negative for HPV. The prevalence of HPV among CC histotypes is very different. It has been suggested that HPV-negative CC may represent a biologically distinct subset of tumors, relying on a distinct pathogenetic pathway and carrying a poorer prognosis, than HPV-positive CCs. Although, the discordance in terms of sensitivity and specificity between different HPV tests as well as the potential errors in sampling and storing tissues may be considered as causes of false-negative results. The identification of HPV-negative CCs is essential for their correct management. The aim of this narrative review is to summarize the clinical and pathological features of this variant. We also discuss the pitfalls of different HPV tests possibly leading to classification errors.

The Role of Ultrasound Guided Sampling Procedures in the Diagnosis of Pelvic Masses: A Narrative Review of the Literature.

Ultrasound-guided sampling methods are usually minimally invasive techniques applied to obtain cytological specimens or tissue samples, mainly used for the diagnosis of different types of tumors. The main benefits of ultrasound guidance is its availability. It offers high flexibility in the choice of sampling approach (transabdominal, transvaginal, and transrectal) and short duration of procedure. Ultrasound guided sampling of pelvic masses represents the diagnostic method of choice in selected patients. We carried out a narrative review of literatures regarding the ultrasound-guided methods of cytological and histological evaluation of pelvic masses as well as the positive and negative predictors for the achievement of an adequate sample.

Management of abdominal wall recurrent subfascial seroma after pelvic surgery.

Seroma is a serous fluid collection that accumulates in dead spaces, where tissue was attached to something before surgery. Abdominal seroma formation is a quite common complication after breast reconstruction with abdominal's flaps or after an abdominoplasty procedure.The most frequently used method for decreasing early seroma frequency are the use of closed suction drains, ultrasonic dissection and sharp dissection, use of fibrine, and use of clip or ligation of vessels during the sur-gery. The management strategies consist of non-operative management, percutaneous drainage, or surgical drainage. With this paper we report a case of a subfascial seroma of the abdominal wall oc-curred in a 41 years old patient after laparotomy surgery for a voluminous pelvic serocele.

Accuracy of Micro-Computed Tomography in Post-mortem Evaluation of Fetal Congenital Heart Disease. Comparison Between Post-mortem Micro-CT and Conventional Autopsy.

Aims: Early prenatal diagnosis of congenital heart disease is feasible. Conventional autopsy is the current gold standard method for post-mortem confirmation. Radiologic techniques alternative to conventional autopsy, such as post-mortem micro-computed tomography, have been proposed in case of limited diagnostic accuracy (i.e., early termination of pregnancy, samples of small dimension or of low weight). The aim of the present study was to define accuracy of micro-computed tomography for post-mortem diagnosis of congenital heart disease in gross anatomy samples. Methods and Results: Fetal heart underwent in-utero prenatal echocardiography and ex-vivo post-mortem evaluation by 9 µm resolution micro-computed tomography and conventional autopsy. For each case, 25 indices of cardiac anatomy were studied by post-mortem micro-computed tomography and conventional autopsy; these were used to compare the two post mortem techniques. Ten samples were examined (gestational age between 12 + 4 and 21 + 6 weeks of gestation). Considering comparable indices, agreement between post-mortem micro-computed tomography and conventional autopsy was of 100% and sensitivity and specificity were of 100%. In "challenging specimens," post-mortem micro-computed tomography diagnoses more indices as compared to conventional autopsy and 84% of "not-diagnostic" indices at conventional autopsy would be diagnostic at post-mortem micro-computed tomography. Conclusion: Micro-computed tomography can be a valid diagnostic alternative to conventional autopsy for post-mortem evaluation of human fetal heart. In addition, it may prove superior to conventional autopsy particularly in cases coming from early termination of pregnancy or in samples of small dimension or of low weight.

Three-Dimensional Printing of Fetal Models of Congenital Heart Disease Derived From Microfocus Computed Tomography: A Case Series.

This article presents a case series of n = 21 models of fetal cardiovascular anatomies obtained from post mortem microfocus computed tomography (micro-CT) data. The case series includes a broad range of diagnoses (e.g., tetralogy of Fallot, hypoplastic left heart syndrome, dextrocardia, double outlet right ventricle, atrio-ventricular septal defect) and cases also had a range of associated extra-cardiac malformations (e.g., VACTERL syndrome, central nervous system anomalies, renal anomalies). All cases were successfully reconstructed from the microfocus computed tomography data, demonstrating the feasibility of the technique and of the protocols, including in-house printing with a desktop 3D printer (Form2, Formlabs). All models were printed in 1:1 scale as well as with the 5-fold magnification, to provide insight into the intra-cardiac structures. Possible uses of the models include education and training.

Prostate cancer specific mortality in the Florence screening pilot study cohort 1992-1993.

The impact of screening on prostate cancer mortality is still unknown. A favourable impact is suggested by uncontrolled and possibly biased studies. Mortality from all causes and from prostate cancer was assessed in a cohort of 6,861 males aged 60-74 years, participants to a pilot screening study during 1991-1994. Observed/expected mortality was determined by linkage with cancer and mortality registries. Prostate cancer standardised mortality rate (SMR) in the overall series (751 subjects excluded by GPs for disabling illness or prostate cancer; 3,448 refusers, 2,662 attenders; 67,321.2 men-year) was 0.96 (95% confidence interval (CI)=0.74-1.22) when deaths from prevalent cancers diagnosed before screening were considered. Reduced prostate cancer mortality (SMR=0.48; 95% CI=0.26-0.83), persisting beyond five years after study entry (SMR=0.48; 95% CI=0.22-0.90), was observed in attenders and not in refusers (SMR=0.99; 95% CI=0.69-1.37). This finding might suggest a screening effect, but might also be ascribed to an healthy screening effect, and cannot be assumed as a reliable evidence of screening efficacy.

Determining overdiagnosis by screening with DRE/TRUS or PSA (Florence pilot studies, 1991-1994).

The rate of overdiagnosis of prostate carcinoma was assessed by following 6890 participants in pilot screening studies from 1991 to 1994. Observed/expected incidence and mortality were determined using data from the Cancer and Mortality Registry. The cancer detection rate (1.75%) and observed/expected ratio (12.5:1) were high at the first screening, and substantially lower at the second screening (0.65% or 4.10:1). According to the registry follow-up, prostate cancer occurred in 225 subjects in the whole study cohort, while 178.2 were expected with 50652 men/years at risk. The standardised incidence rate was 1.66 in the screened (95%CI=1.4-2.0), 0.97 in the non-responders (95%CI=0.8-1.2) and 1.23 in subjects excluded from invitation due to previous cancer or major illness (95%CI=0.8-1.5). A 66% excess incidence rate was observed in the screened subjects over a 9-year period, confirming previous estimates of overdiagnosis.