A multilayer perceptron-based model applied to histopathology image classification of lung adenocarcinoma subtypes.

Objective: Lung cancer is one of the most common malignant tumors in humans. Adenocarcinoma of the lung is another of the most common types of lung cancer. In clinical medicine, physicians rely on the information provided by pathology tests as an important reference for the fifinal diagnosis of many diseases. Thus, pathological diagnosis is known as the gold standard for disease diagnosis. However, the complexity of the information contained in pathology images and the increase in the number of patients far exceeds the number of pathologists, especially in the treatment of lung cancer in less-developed countries. Methods: This paper proposes a multilayer perceptron model for lung cancer histopathology image detection, which enables the automatic detection of the degree of lung adenocarcinoma infifiltration. For the large amount of local information present in lung cancer histopathology images, MLP IN MLP (MIM) uses a dual data stream input method to achieve a modeling approach that combines global and local information to improve the classifification performance of the model. In our experiments, we collected 780 lung cancer histopathological images and prepared a lung histopathology image dataset to verify the effectiveness of MIM. Results: The MIM achieves a diagnostic accuracy of 95.31% and has a precision, sensitivity, specificity and F1-score of 95.31%, 93.09%, 93.10%, 96.43% and 93.10% respectively, outperforming the diagnostic results of the common network model. In addition, a number of series of extension experiments demonstrated the scalability and stability of the MIM. Conclusions: In summary, MIM has high classifification performance and substantial potential in lung cancer detection tasks.

CroReLU: Cross-Crossing Space-Based Visual Activation Function for Lung Cancer Pathology Image Recognition.

Lung cancer is one of the most common malignant tumors in human beings. It is highly fatal, as its early symptoms are not obvious. In clinical medicine, physicians rely on the information provided by pathology tests as an important reference for the final diagnosis of many diseases. Therefore, pathology diagnosis is known as the gold standard for disease diagnosis. However, the complexity of the information contained in pathology images and the increase in the number of patients far outpace the number of pathologists, especially for the treatment of lung cancer in less developed countries. To address this problem, we propose a plug-and-play visual activation function (AF), CroReLU, based on a priori knowledge of pathology, which makes it possible to use deep learning models for precision medicine. To the best of our knowledge, this work is the first to optimize deep learning models for pathology image diagnosis from the perspective of AFs. By adopting a unique crossover window design for the activation layer of the neural network, CroReLU is equipped with the ability to model spatial information and capture histological morphological features of lung cancer such as papillary, micropapillary, and tubular alveoli. To test the effectiveness of this design, 776 lung cancer pathology images were collected as experimental data. When CroReLU was inserted into the SeNet network (SeNet_CroReLU), the diagnostic accuracy reached 98.33%, which was significantly better than that of common neural network models at this stage. The generalization ability of the proposed method was validated on the LC25000 dataset with completely different data distribution and recognition tasks in the face of practical clinical needs. The experimental results show that CroReLU has the ability to recognize inter- and intra-class differences in cancer pathology images, and that the recognition accuracy exceeds the extant research work on the complex design of network layers.

Prenatal diagnosis of fetal congenital mesoblastic nephroma by ultrasonography combined with MR imaging: A case report and literature review.

RATIONALE: Fetal congenital mesoblastic nephroma (CMN) is a rare renal tumor, characterized by polyhydramnios, premature birth, and neonatal hypertension. In the prenatal stage, it is particularly difficult to diagnose CMN either by ultrasonography or magnetic resonance imaging (MRI). Thus, CMN is frequently detected in the third trimester in the clinical scenario. PATIENT CONCERNS: A 29-year-old G2P0 pregnant woman took routine prenatal examinations in our hospital. The fetal right kidney abnormality was not observed after 2 systematical ultrasonic examinations (at 24 and 31 weeks of gestation respectively), and only an increase was noticed in the amniotic fluid index (from 19.3 to 20.8 cm). DIAGNOSIS: CMN was detected by antenatal ultrasonography and MRI as a fetal right renal mass at 35 weeks of gestation in our hospital. INTERVENTIONS: The pregnant woman was admitted at a gestational age of 38 weeks and 5 days due to alterations in renal function. Further, the pregnant woman was administered with "oxytocin" to promote delivery, and the neonate underwent a right nephrectomy on the 9th day after birth. OUTCOMES: The pathological examination confirmed a cellular type of right CMN. The neonate recovered well after operation without adjuvant treatment. During 6 months of follow-up, the neonate grew well and showed no signs of recurrence or metastasis. CONCLUSION: Polyhydramnios detected during prenatal examination required attention due to the risk of malformation of fetal urinary system. Prenatal ultrasonography combined with MRI could not only clearly identify the origin of the tumor, but also distinguish the correlation between the tumor and adjacent structures, thereby leading to early diagnosis and favorable prognosis.

Mucinous tubular and spindle cell carcinoma of the kidney: A case report and review of the literature.

Mucinous tubular and spindle cell carcinoma of the kidney (MTSCC-K) is an unusual renal tumor. It is important to increase the recognition of MTSCC-K and improve the level of clinical diagnosis. The current study presents a case of MTSCC-K with clinical, imaging and pathological examination. A 60-year-old female presented to the First Hospital of Jilin University suffering from lumbodorsalgia on the right side for approximately one month, without gross hematuria and fever. Imaging examination by abdominal computed tomography scan revealed a ~6.5×5.0-cm solid mass in the inferior pole of the right kidney. The patient underwent laparoscopic radical resection of the right kidney. Pathological examination showed that the tumor was composed of small, elongated cords or tubules, in a tightly packed arrangement. Myxoid stroma was shown to be interspersed among the tubular cells, and appeared to exhibit slender tubular spindle cell-like structures. Tumor cells were smaller and cube-shaped or oval, with single small eosinophilic nucleoli and low-grade nuclei. Occasionally, necrosis and foam cell infiltration were observed. Myxoid stroma was stained by acidic mucus. Immunohistochemical markers, including CK7, CK19, EMA, Vimentin and P504S (AMACR) showed positive expression in tumoral cells, but the tumoral cells were CD10-negative. The MTSCC-K is a low-grade polymorphic renal epithelial neoplasm, which may be diagnosed by immunohistochemistry. The patients are likely to have an improved prognosis following surgery compared with patients with other renal cell carcinomas.

Holmium laser enucleation of the prostate versus transurethral resection of the prostate: a randomized clinical trial.

OBJECTIVE: To evaluate the efficacy and safety of holmium laser enucleation of the prostate (HoLEP) and transurethral resection of the prostate (TURP), for treatment of benign prostatic hyperplasia (BPH). METHODS: A total of 164 cases of BPH were selected from patients who were hospitalized between January 2010 and December 2011. Patients had received either HoLEP or TURP treatment. Clinical data were collected from the perioperative period, 1 month after surgery, and 12 months after surgery. RESULTS: There was no significant difference between the two groups in the maximum urinary flow rate (Q max), postvoid residual volume (PVR), international prostate symptom score (IPSS), or quality-of-life score (QOL score) at 1 month after surgery (p = 0.56, p = 0.346, p = 0.536 and p = 0.145, respectively). However, after 12 months, patients from the HoLEP group demonstrated better scores in Qmax, PVR, IPSS, and QOL than those from the TURP group (p = 0.037, p = 0.003, p < 0.001 and p = 0.019, respectively). The two groups had comparable operation time (p = 0.105), catheterization time (p = 0.173), and length of hospital stay (p = 0.395), but were statistically different in the weight of resected prostate tissue (p < 0.001), bladder irrigation time (p < 0.001), hemoglobin levels (p = 0.011), and blood sodium levels (p = 0.002) after surgery. CONCLUSIONS: Compared to TURP, HoLEP was safer and had better long-term efficacy as assessed by multiple quantitative measures. Therefore, HoLEP may present a better option in the treatment of BPH.