AI-powered real-time annotations during urologic surgery: The future of training and quality metrics.

INTRODUCTION AND OBJECTIVE: Real-time artificial intelligence (AI) annotation of the surgical field has the potential to automatically extract information from surgical videos, helping to create a robust surgical atlas. This content can be used for surgical education and qualitative initiatives. We demonstrate the first use of AI in urologic robotic surgery to capture live surgical video and annotate key surgical steps and safety milestones in real-time. SUMMARY BACKGROUND DATA: While AI models possess the capability to generate automated annotations based on a collection of video images, the real-time implementation of such technology in urological robotic surgery to aid surgeon and training staff it is still pending to be studied. METHODS: We conducted an educational symposium, which broadcasted 2 live procedures, a robotic-assisted radical prostatectomy (RARP) and a robotic-assisted partial nephrectomy (RAPN). A surgical AI platform system (Theator, Palo Alto, CA) generated real-time annotations and identified operative safety milestones. This was achieved through trained algorithms, conventional video recognition, and novel Video Transfer Network technology which captures clips in full context, enabling automatic recognition and surgical mapping in real-time. RESULTS: Real-time AI annotations for procedure #1, RARP, are found in Table 1. The safety milestone annotations included the apical safety maneuver and deliberate views of structures such as the external iliac vessels and the obturator nerve. Real-time AI annotations for procedure #2, RAPN, are found in Table 1. Safety milestones included deliberate views of structures such as the gonadal vessels and the ureter. AI annotated surgical events included intraoperative ultrasound, temporary clip application and removal, hemostatic powder application, and notable hemorrhage. CONCLUSIONS: For the first time, surgical intelligence successfully showcased real-time AI annotations of 2 separate urologic robotic procedures during a live telecast. These annotations may provide the technological framework for send automatic notifications to clinical or operational stakeholders. This technology is a first step in real-time intraoperative decision support, leveraging big data to improve the quality of surgical care, potentially improve surgical outcomes, and support training and education.

Robotic nephroureterectomy supplanting open and laparoscopic approach for upper tract urothelial carcinoma management: a narrative review.

Background and Objective: The use of robotic surgery for managing upper tract urothelial carcinoma (UTUC) has increased significantly over the years. Minimally invasive techniques (MIS) are now used for approximately half of all robot-assisted laparoscopic nephroureterectomy (RAL-NU) performed in the USA. However, there are currently no specific management guidelines that recommend the use of a robotic approach, and the available literature on this topic is limited. For this reason, we reviewed the history and current literature regarding this technique. Methods: We searched Web of Science and PubMed for articles between 1934 to 2023 using 20 different search terms and combinations. We restricted our selection to only publications in English language. Key Content and Findings: Comparative retrospective studies between techniques [open nephroureterectomy (ONU), laparoscopic nephroureterectomy (LNU), and RAL-NU] and case series of surgical groups, mostly at short- and mid-term follow-up, were included. Conclusions: Robotic surgery for UTUC is on the rise and is predicted to become the preferred method for nephroureterectomy. A comparison of RAL-NU to LNU and ONU shows several advantages, including less blood loss, pain, and hospital stay, as well as a quicker recovery time. The safety and effectiveness of robotic surgery for lymphadenectomy also supports its use in RAL-NU. As more medical facilities adopt the technique and further studies support its benefits, it is likely that robotic surgery will become the preferred method for NU.

Complications of single-port robot-assisted radical prostatectomy: multi-institutional analysis from the Single-Port Advanced Research Consortium (SPARC).

OBJECTIVE: To evaluate the perioperative complications of single-port robot-assisted radical prostatectomy (SP-RARP). PATIENTS AND METHODS: A retrospective review was performed on the prospectively maintained, Institutional Review Board-approved, multi-institutional Single-Port Advanced Research Consortium (SPARC) database. A total of 1103 patients were identified who underwent three different approaches of SP-RARP between 2019 and 2022 using the purpose-built SP robotic platform. In addition to baseline clinical, perioperative outcomes, this study comprehensively analysed for any evidence of intraoperative complication, as well as postoperative complication and readmission within 90 days of the respective surgery. RESULTS: Of the 244, 712, and 147 patients who underwent transperitoneal, extraperitoneal, and transvesical SP-RARP, respectively, intraoperative complications were noted in five patients (0.4%), all of which occurred during the transperitoneal approach. Two patients had bowel serosal tears, two had posterior button-holing of the bladder necessitating repair, and one patient had an obturator nerve injury. Postoperative complications were noted in 143 patients (13%) with major complications (Clavien-Dindo Grade ≥III) only identified in 3.7% of the total cohort. The most common complications were lymphocele (3.9%), acute urinary retention (2%), and urinary tract infection (1.9%). The 90-day re-admission rate was 3.9%. CONCLUSION: The SP-RARP is a safe and effective procedure with low complication and readmission rates regardless of the approach. These results are comparable to current multi-port RARP literature.

A framework based on the information domain to measure coupling changes in electrophysiological signals.

Objectives.In this paper, the features of physiological signals of healthy dataset are extracted using the linear and non-linear techniques, and a comparison has been made on healthy young and old subjects to study the aging and gender-related changes in the contribution of Heart Rate (HR), Blood Pressure (BP), and Respiration (RESP).Methods. To quantify the coupling changes in cardiovascular, cardiorespiratory, and vasculorespiratory complexity, an information domain approach based on compensated transfer entropy (cTE) is proposed.Result. The results show that there is a substantial decrease in the flow of information from BP tro the time interval between successive R-peaks (RR) and from RR to BP. There is also a significant decrease in the flow of information from RESP to BP and RESP to RR but there is no significant change in the information flow from BP to RESP and RR to RESP.Conclusion. We have done linear and non-linear analysis on the healthy datasets of young and old subjects. As already existed techniques lacks in studying complex behaviours of electrophysiological signals so to overcome these limitations, we have proposed compensated transfer entropy (cTE). We conducted an investigation to determine the degree to which recordings of RESP, BP, and HR can be utilized to predict changes in the other parameters. Specifically, the proposed analysis examined the relationship between these variables and assessed their consistency across different age groups and genders. By analyzing the data, we aimed to gain insights into the interdependencies and predictive potential of these physiological measures in relation to each other.

Transperitoneal Versus Retroperitoneal Single-port Robotic-assisted Partial Nephrectomy: An Analysis from the Single Port Advanced Research Consortium.

BACKGROUND: In the surgical management of kidney tumors, such as in multiport technology, single-port (SP) robotic-assisted partial nephrectomy (RAPN) can be performed using the transperitoneal (TP) or retroperitoneal (RP) approach. However, there is a dearth of literature on the efficacy and safety of either approach for SP RAPN. OBJECTIVE: To compare the peri- and postoperative outcomes of the TP and RP approaches for SP RAPN. DESIGN, SETTING, AND PARTICIPANTS: This is a retrospective cohort study using data from the Single Port Advanced Research Consortium (SPARC) database of five institutions. All patients underwent SP RAPN for a renal mass between 2019 and 2022. INTERVENTION: TP versus RP SP RAPN. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Baseline characteristics, and peri- and postoperative outcomes were compared between both the approaches using χ2 test, Fisher exact test, Mann-Whitney U test, and Student t test. RESULTS AND LIMITATIONS: A total of 219 patients (121 [55.25%] TP, 98 [44.75%] RP) were included in the study. Of them, 115 (51.51%) were male, and the mean age was 60 ± 11 yr. RP had a significantly higher proportion of posterior tumors (54 [55.10%] RP vs 28 [23.14%] TP, p < 0.001), while other baseline characteristics were comparable between both the approaches. There was no statistically significant difference in ischemia time (18 ± 9 vs 18 ± 11 min, p = 0.898), operative time (147 ± 67 vs 146 ± 70 min, p = 0.925), estimated blood loss (p = 0.167), length of stay (1.06 ± 2.25 vs 1.33 ± 1.05 d, p = 0.270), overall complications (5 [5.10%] vs 7 [5.79%]), and major complication rate (2 [2.04%] vs 2 [1.65%], p = 1.000). No difference was observed in positive surgical margin rate (p = 0.472) or delta eGFR at median 6-mo follow-up (p = 0.273). Limitations include retrospective design and no long-term follow-up. CONCLUSIONS: With proper patient selection based on patient and tumor characteristics, surgeons can opt for either the TP or the RP approach for SP RAPN, and maintain satisfactory outcomes. PATIENT SUMMARY: The use of a single port (SP) is a novel technology for performing robotic surgery. Robotic-assisted partial nephrectomy (RAPN) is a surgery to remove a portion of the kidney due to kidney cancer. Depending on patient characteristics and surgeons' preference, SP can be performed via two approaches for RAPN: through the abdomen or through the space behind the abdominal cavity. We compared outcomes between these two approaches for patients receiving SP RAPN, finding that they were comparable. We conclude that with proper patient selection based on patient and tumor characteristics, surgeons can opt for either the TP or the RP approach for SP RAPN, and maintain satisfactory outcomes.

Low Risk of Postoperative Hernia Following Single-port Robot-assisted Radical Prostatectomy: A Report From the Single-port Advanced Research Consortium (SPARC).

OBJECTIVE: To evaluate the risk of postoperative hernia following different approaches of single-port robot-assisted radical prostatectomy (SP-RARP). METHODS: A retrospective review was performed on patients who underwent SP-RARP between February 2019 and December 2022. Demographic and clinical information was collected from the multi-institutional, prospectively-maintained Single-Port Advanced Research Consortium (SPARC) database. Data were analyzed using IBM Statistical Packaging for Social Sciences (SPSS) version 29.0 with descriptive statistics as presented. RESULTS: A total of 1103 patients were identified, consisting of 244 (22.1%), 712 (64.6%), and 147 (13.3%) cases performed via transperitoneal, extraperitoneal (EP), and transvesical (TV) approaches, respectively. During a median follow-up time of 11 months (interquartile range 5.7-17.1 months), only two cases of incisional hernia were reported. Both cases occurred following transperitoneal SP-RARP with one patient requiring surgical repair. There remains no evidence of postoperative hernia following EP and TV SP-RARP at the completion of our review. CONCLUSION: SP-RARP was associated with low risk for postoperative hernia. The risk was lower following TV and EP SP-RARP where the peritoneum is preserved.

Trends in the surgical management of kidney cancer by tumor stage, treatment modality, facility type, and location.

Partial nephrectomy (PN) is an alternative to radical nephrectomy (RN) in the appropriate localized renal tumor. The scope of PN has expanded over time and, since the advent and proliferation of minimally invasive surgery, more surgeons have access to and have been trained in laparoscopic and robotic technology. Amid the changing surgical landscape, we sought to characterize the trends in management by cancer stage, institution type, and geographic location using the National Cancer Database (NCDB). We queried the NCDB for patients with kidney cancer from 2004 to 2019. Overall, 241,311 patients who underwent PN or RN were included in the study. The nephrectomy approach was categorized as robotic partial (RPN), robotic radical (RRN), laparoscopic partial (LPN), laparoscopic radical (LRN), open or unspecified partial (OPN), and open or unspecified radical (ORN). The categorical variables were presented as frequency and percentages. Overall, there was an increase in the utilization of robotic approaches from 2010 to 2019. For cT1 tumors, the use of RPN and RRN increased from 14.27 to 33.06% and 5.24% to 19.63%, respectively. The use of ORN for cT2 and cT3 tumors declined, with rates dropping from 54.71 to 10.76% and 64.71 to 46.64%, respectively. Conversely, the utilization of RRN rose during this period. However, ORN remained the most common approach for cT3 tumors. The use of RPN increased across different facility types, with the highest utilization observed in academic/research programs. The use of ORN for cT2 and cT3 tumors declined across facility types, although it remained most prevalent in community cancer programs. The use of robot-assisted surgery to treat localized renal cancer increased in the US between 2010 and 2019 across all stages of disease. RPN became the most used approach for cT1 disease, while LRN was preferred for cT2 disease. ORN remained the approach of choice for cT3 disease throughout the study period. Trends in facility type and geographic location largely mirrored the overall trends.

Robot-assisted partial nephrectomy for complex renal tumors: Analysis of a large multi-institutional database.

INTRODUCTION: Highly complex renal masses pose a challenge to urologic surgeons' ability to perform robotic partial nephrectomy (RPN). Given the increased utilization of the robotic approach for small renal masses, we sought to characterize the outcomes and determine the safety and feasibility of RPN for complex renal masses from our large multi-institutional cohort. METHODS: We performed a retrospective analysis of patients with R.E.N.A.L. Nephrometry Scores ≥10 who underwent RPN in our multi-institutional cohort (N = 372). Baseline demographic, clinical and tumor related characteristics were evaluated with the primary endpoint of trifecta achievement (defined as negative surgical margin, no major complications, and warm ischemia time ≤25 min). Relationships between variables were assessed using the chi-square test of independence, Fisher exact test, Mann-Whitney U test, and Kruskal Wallis test. Logistic regression was used to evaluate the relationship between baseline characteristics and trifecta achievement. RESULTS: Of 372 patients in the study, mean age was 58 years, and median BMI was 30.49 kg/m2. The median tumor size was 4.3 cm (3.0-5.9 cm). Most of the patients had R.E.N.A.L. scores of 10 (n = 253; 67.01%). Overall, trifecta was achieved in 72.04% of patients. Stratifying intraoperative and postoperative outcomes by R.E.N.A.L. scores, there was no significant difference in trifecta achievement, operative time, warm ischemia time (WIT), open conversion, major complication, or positive margin rates. Length of hospital stay was significantly longer for higher R.E.N.A.L. scores (median days 2 vs. 1, P = 0.012). Multivariate analyses for factors associated with trifecta achievement concluded that age and baseline eGFR were independently associated with trifecta achievement. CONCLUSION: RPN is a safe and reproducible procedure for complex tumors with R.E.N.A.L. Nephrometry scores ≥10. Our results suggest excellent rates of trifecta achievement and short-term functional outcomes when performed by experienced surgeons. Long-term oncological and functional evaluation are needed to further support this conclusion.

Transperitoneal Versus Retroperitoneal Robotic-Assisted Partial Nephrectomy in Patients with Obesity.

Introduction: We aim to compare transperitoneal (TP) and retroperitoneal (RP) robotic partial nephrectomy (RPN) in obese patients. Obesity and RP fat can complicate RPN, especially in the RP approach where working space is limited. Materials and Methods: Using a multi-institutional database, we analyzed 468 obese patients undergoing RPN for a renal mass (86 [18.38%] RP, 382 [81.62%] TP). Obesity was defined as body mass index ≥30 kg/m2*. A 1:1 propensity score matching was performed adjusting for age, previous abdominal surgery, tumor size, R.E.N.A.L nephrometry score, tumor location, surgical date, and participating centers. Baseline characteristics and perioperative and postoperative data were compared. Results: In the propensity score-matched cohort, 79 (50%) TP patients were matched with 79 (50%) RP patients. The RP group had more posterior tumors (67 [84.81%], RP versus 23 [29.11%], TP; P < .001), while the other baseline characteristics were comparable. Warm ischemia time (interquartile range; 15 [10, 12], RP versus 14 [10, 17] minutes, TP; P = .216), operative time (129 [116, 165], RP versus 130 [95, 180] minutes, TP; P = .687), estimated blood loss (50 [50, 100], RP versus 75 [50, 150] mL, TP; P = .129), length of stay (1 [1, 1], RP versus 1 [1, 2] day, TP; P = .319), and major complication rate (1 [1.27%], RP versus 3 [3.80%], TP; P = .620) were similar. No significant difference was observed in positive surgical margin rate and delta estimated glomerular filtration at follow-up. Conclusion: TP and RP RPN yielded similar perioperative and postoperative outcomes in obese patients. Obesity should not be a factor in determining optimal approach for RPN.

Operative and oncological outcomes of salvage robotic radical and partial nephrectomy: a multicenter experience.

We aim to describe the perioperative and oncological outcomes for salvage robotic partial nephrectomy (sRPN) and salvage robotic radical nephrectomy (sRRN). Using a prospectively maintained multi-institutional database, we compared baseline clinical characteristics and perioperative and postoperative outcomes, including pathological stage, tumor histology, operative time, ischemia time, estimated blood loss (EBL), length of stay (LOS), postoperative complication rate, recurrence rate, and mortality. We identified a total of 58 patients who had undergone robotic salvage surgery for a recurrent renal mass, of which 22 (38%) had sRRN and 36 (62%) had sRPN. Ischemia time for sRPN was 14 min. The median EBL was 100 mL in both groups (p = 0.581). One intraoperative complication occurred during sRRN, while three occurred during sRPN cases (p = 1.000). The median LOS was 2 days for sRRN and 1 day for sRPN (p = 0.039). Postoperatively, one major complication occurred after sRRN and two after sRPN (p = 1.000). The recurrence reported after sRRN was 5% and 3% after sRPN. Among the patients who underwent sRRN, the two most prevalent stages were pT1a (27%) and pT3a (27%). Similarly, the two most prevalent stages in sRPN patients were pT1a (69%) and pT3a (6%). sRRN and sRPN have similar operative and perioperative outcomes. sRPN is a safe and feasible procedure when performed by experienced surgeons. Future studies on large cohorts are essential to better characterize the importance and benefit of salvage partial nephrectomies.

Single Port Versus Multiport Robot-assisted Simple Prostatectomy: A Multi-institutional Study From the Single-port Advanced Research Consortium (SPARC).

OBJECTIVE: To compare robot-assisted simple prostatectomy intraoperative and postoperative.ßoutcomes between single-port (SP) and multiport (MP) robotic systems in a multi-institutional setting. METHODS: We analyzed all-consecutive robot-assisted simple prostatectomy cases done in 5 centers from January 2017 to October 2022. Data were analyzed with descriptive statistics and compared with appropriate tests depending on the type of variable and distribution. Statistical significance was considered when P.ß<.05. RESULTS: A total of 405 cases were analyzed:.ß249 and 156 were MP and SP, respectively. Operative times were similar between groups (P.ß=.ß.62). Estimated blood loss during surgery was significantly lower with the SP robot (P.ß<.001). Postoperatively, the SP approach required a significantly shorter hospital stay, less use of opioids, and a shorter duration of Foley catheter (P.ß<.001). There was no significant difference between the post-operative Clavien-Dindo ...3 complication rate (P.ß=.ß.30). The 30-day readmission rate of MP (10.8%) was significantly higher than for SP (0%) (P.ß<.001). De novo urge incontinence was more common in the MP group (P.ß=.ß.02). CONCLUSION: The SP robotic approach to simple prostatectomy is advantageous when it comes to postoperative comfort for patients. Specifically, it requires a shorter hospital stay, less use of opioids, and a shorter Foley catheter duration.

The State of Robotic Partial Nephrectomy: Operative, Functional, and Oncological Outcomes From A Robust Multi-Institution Collaborative.

OBJECTIVE: To describe the most recent surgical, functional, and oncological outcomes of RPN utilizing one of the largest, prospectively maintained, multi-institution consortium of patients undergoing robotic renal surgery. MATERIALS AND METHODS: Data was obtained from a prospectively maintained multi-institutional database of patients who underwent RPN for clinically localized kidney cancer between 2018 and 2022 by 9 high-volume surgeons. Demographic and tumor characteristics as well as operative, functional, and oncological outcomes were queried. RESULTS: A total of 2836 patients underwent RPN. Intraoperative, postoperative, and 30-day major complication rates were 2.68%, 11.39%, and 3.24%, respectively. Median tumor size was 3.0 cm. Tumors with low complexity had a shorter median operative time, lower median EBL, shorter median ischemia time, lower postoperative complication rate, and lower decline in renal function There was no significant difference between tumor complexities with respect to the rate of conversion to radical nephrectomy, conversion to open, major complications, and positive margins. Lower BMI, smaller clinical tumor size, lower tumor complexity, and higher baseline eGFR were significantly associated with trifecta achievement. CONCLUSION: Patient BMI, baseline eGFR, and tumor characteristics such as size and complexity are the most important predictors of trifecta achievement. Patients with complex tumors should be counseled that they are at increased risk of complications and worsening renal function after robotic partial nephrectomy.

A comparison of outcomes between transperitoneal and retroperitoneal robotic assisted partial nephrectomy in patients with completely endophytic kidney tumors.

INTRODUCTION: Retroperitoneal robotic partial nephrectomy (RPN) has been shown to have comparable outcomes to the transperitoneal approach for renal tumors. However, this may not be true for completely endophytic tumors as they pose significant challenges in RPN with increased complication rates. Hence, we sought to compare the safety and feasibility of retroperitoneal RPN to transperitoneal RPN for completely endophytic tumors. METHODS: We performed a retrospective analysis of patients who underwent RPN for a completely endophytic renal mass using either transperitoneal or retroperitoneal approach from our multi-institutional database (n = 177). Patients who had a solitary kidney, prior ipsilateral surgery, multiple/bilateral tumors, and horseshoe kidneys were excluded from the analysis. Overall, 156 patients were evaluated (112 [71.8%] transperitoneal, 44 [28.2%] retroperitoneal). Baseline characteristics, perioperative and postoperative data were compared between the surgical transperitoneal and retroperitoneal approach using Chi-square test, Fishers exact test, t test, Mood median test and Mann Whitney U test. RESULTS: Of the 156 patients in this study, 86 (56.9%) were male and the mean (SD) age was 58 (13) years. Baseline characteristics were comparable between the 2 approaches. Compared to transperitoneal approach, retroperitoneal approach had similar ischemia time (19.6 [SD = 7.6] minutes vs. 19.5 [SD = 10.2] minutes, P = 0.952), operative time (157.5 [SD = 44.8] minutes vs. 160.2 [SD = 47.3] minutes, P = 0.746), median estimated blood loss (50 ml [IQR: 50, 150] vs. 100 ml [IQR: 50, 200], P = 0.313), median length of stay (1 [IQR: 1, 2] day vs. 1 [IQR: 1, 2] day, P = 0.126) and major complication rate (2 [4.6%] vs. 3 [2.7%], P = 0.621). No difference was observed in positive surgical margin rate (P = 0.1.00), delta eGFR (P = 0.797) and de novo chronic kidney disease occurrence (P = 1.000). CONCLUSION: Retroperitoneal and transperitoneal RPN yielded similar perioperative and functional outcomes in patients with completely endophytic tumors. In well-selected patients with purely endophytic tumors, either a retroperitoneal or transperitoneal approach could be considered without compromising perioperative and postoperative outcomes.

Classification of various nutrient deficiencies in tomato plants through electrophysiological signal decomposition and sample space reduction.

Plants leave testimonies of undergoing physical state by depicting distinct variations in their electrophysiological data. Adequate nutrition of plants signifies their role in the growth and a plentiful harvest. Plant signal data carries enough information to detect and analyse nutrient deficiency. Classification of nutrient deficiencies through signal decomposition and bilevel measurements has not been reported earlier. The proposed work explores tomato plants in four-time cycles (Early Morning, Morning, After Noon, Night) of macronutrients Calcium (Ca), Nitrogen (N) and micronutrients Manganese (Mn), Iron (Fe). Using the Empirical Mode Decomposition method (EMD), signals are decomposed into Intrinsic Mode Functions (IMF) in 10-levels. Further, Intrinsic mode functions are grouped into two clusters to extract descriptive data statistics and bi-level measurements. Then a novel sample selection method is proposed to achieve a better classification rate by reducing sample space. A binary classification model is built to train and test 15 features individually using discriminant analysis and naïve-Bayes classifier variants. The reported results achieved a classification rate up to 98% after 5-fold cross-validation. Attained findings endorse novel pathways for detection and classification of nutrient deficiencies in the early stages, consequently promoting prevention and treatment approaches earliest to the appearance of symptoms, also helping to enhance plant growth.

Multi-label segmentation and detection of COVID-19 abnormalities from chest radiographs using deep learning.

Due to COVID-19, demand for Chest Radiographs (CXRs) have increased exponentially. Therefore, we present a novel fully automatic modified Attention U-Net (CXAU-Net) multi-class segmentation deep model that can detect common findings of COVID-19 in CXR images. The architectural design of this model includes three novelties: first, an Attention U-net model with channel and spatial attention blocks is designed that precisely localize multiple pathologies; second, dilated convolution applied improves the sensitivity of the model to foreground pixels with additional receptive fields valuation, and third a newly proposed hybrid loss function combines both area and size information for optimizing model. The proposed model achieves average accuracy, DSC, and Jaccard index scores of 0.951, 0.993, 0.984, and 0.921, 0.985, 0.973 for image-based and patch-based approaches respectively for multi-class segmentation on Chest X-ray 14 dataset. Also, average DSC and Jaccard index scores of 0.998, 0.989 are achieved for binary-class segmentation on the Japanese Society of Radiological Technology (JSRT) CXR dataset. These results illustrate that the proposed model outperformed the state-of-the-art segmentation methods.

A morphologically robust chaotic map based approach to embed patient's confidential data securely in non-QRS regions of ECG signal.

In e-healthcare paradigm, the physiological signals along with patient's personal information need to be transmitted to remote healthcare centres. Before sharing this sensitive information over the unsecured channel, it is prerequisite to protect it from unauthorised access. The proposed method explores ECG signal as the cover signal to hide patient's personal information without disturbing its diagnostic features. Chaotic maps are used to randomly select the embedding locations in the non-QRS region while excluding the sensitive QRS region of ECG train. Optimum Location Selection algorithm has been designed to select the embedding locations in non-QRS embedding region. The proposed algorithm is thoroughly examined and the distortion is measured in terms of statistical parameters and clinical measures such as PRD, PRDN, PRD1024, PSNR, SNR, MSE, MAE, KL-Divergence, WWPRD and WEDD. The robustness of the algorithm is verified using the parameters such as key space and key sensitivity. The implementation has been extensively tested on all the 48 records of the standard MIT-BIH Arrhythmia database, abnormal databases [CU-VT, BIDMC-CHF and PTB (leads I, II and III)] and self-recorded data of 20 subjects. The algorithm yields average PRD, MSE, KL-Divergence, PSNR, WWPRD and WEDD of 4.7 × 10-3, 1.13 × 10-5, 1.29 × 10-5, 50.28, 0.15 and 0.04 at an average maximum EC of 0.45(96876 bits) on MIT-BIH Arrhythmia database and 0.016, 3.38 × 10-5, 1.8 × 10-4, 46.03, 0.13 and 0.03 respectively at an average maximum EC of 0.47 (102571 bits) on self-recorded data which clearly reveals the competency of the proposed algorithm in comparison with the other state of the art ECG steganography approaches.

Alexander fractional differential window filter for ECG denoising.

The electrocardiogram (ECG) non-invasively monitors the electrical activities of the heart. During the process of recording and transmission, ECG signals are often corrupted by various types of noises. Minimizations of these noises facilitate accurate detection of various anomalies. In the present paper, Alexander fractional differential window (AFDW) filter is proposed for ECG signal denoising. The designed filter is based on the concept of generalized Alexander polynomial and the R-L differential equation of fractional calculus. This concept is utilized to formulate a window that acts as a forward filter. Thereafter, the backward filter is constructed by reversing the coefficients of the forward filter. The proposed AFDW filter is then obtained by averaging of the forward and backward filter coefficients. The performance of the designed AFDW filter is validated by adding the various type of noise to the original ECG signal obtained from MIT-BIH arrhythmia database. The two non-diagnostic measure, i.e., SNR, MSE, and one diagnostic measure, i.e., wavelet energy based diagnostic distortion (WEDD) have been employed for the quantitative evaluation of the designed filter. Extensive experimentations on all the 48-records of MIT-BIH arrhythmia database resulted in average SNR of 22.014 ± 3.806365, 14.703 ± 3.790275, 13.3183 ± 3.748230; average MSE of 0.001458 ± 0.00028, 0.0078 ± 0.000319, 0.01061 ± 0.000472; and average WEDD value of 0.020169 ± 0.01306, 0.1207 ± 0.061272, 0.1432 ± 0.073588, for ECG signal contaminated by the power line, random, and the white Gaussian noise respectively. A new metric named as morphological power preservation measure (MPPM) is also proposed that account for the power preservance (as indicated by PSD plots) and the QRS morphology. The proposed AFDW filter retained much of the original (clean) signal power without any significant morphological distortion as validated by MPPM measure that were 0.0126, 0.08493, and 0.10336 for the ECG signal corrupted by the different type of noises. The versatility of the proposed AFDW filter is also validated by its application on the ECG signal from MIT-BIH database corrupted by the combination of the noises as well as on the real noisy ECG signals are taken from MIT-BIH ID database. Furthermore, the comparative study has also been done between the proposed AFDW filter and existing state of the art denoising algorithms. The results clearly prove the supremacy of our proposed AFDW filter.

Design of tree structured matched wavelet for HRV signals of menstrual cycle.

An algorithm is presented for designing a new class of wavelets matched to the Heart Rate Variability (HRV) signals of the menstrual cycle. The proposed wavelets are used to find HRV variations between phases of menstrual cycle. The method finds the signal matching characteristics by minimising the shape feature error using Least Mean Square method. The proposed filter banks are used for the decomposition of the HRV signal. For reconstructing the original signal, the tree structure method is used. In this approach, decomposed sub-bands are selected based upon their energy in each sub-band. Thus, instead of using all sub-bands for reconstruction, sub-bands having high energy content are used for the reconstruction of signal. Thus, a lower number of sub-bands are required for reconstruction of the original signal which shows the effectiveness of newly created filter coefficients. Results show that proposed wavelets are able to differentiate HRV variations between phases of the menstrual cycle accurately than standard wavelets.

Adaptive correlation dimension method for analysing heart rate variability during the menstrual cycle.

Correlation dimension (CD) is used for analysing the chaotic behaviour of the nonlinear heart rate variability (HRV) time series. In CD, the autocorrelation function is used to calculate the time delay. However, it does not provide optimum values of time delays, which leads to an inaccurate estimation of the HRV between phases of the menstrual cycle. Thus, an adaptive CD method is presented here to calculate the optimum value of the time delay based upon the information content in the HRV signal. In the proposed method, the first step is to divide the HRV signal into overlapping windows. Afterwards, the time delay is calculated for each window based on the features of the signal. This procedure of finding the optimum time delay for each window is known as adaptive autocorrelation. Then, the CD for each window is calculated using optimum time delays. Finally, adaptive CD is calculated by averaging the CD of all windows. The proposed method is applied on two data sets: (i) the standard Physionet dataset and (ii) the dataset acquired using BIOPAC(®)MP150. The results show that the proposed method can accurately differentiate between normal and diseased subjects. Further, the results prove that the proposed method is more accurate in detecting HRV variations during the menstrual cycles of 74 young women in lying and standing postures. Three statistical parameters are used to find the effectiveness of adaptive autocorrelation in calculating time delays. The comparative analysis validates the superiority of the proposed method over detrended fluctuation analyses and conventional CD.

K-nearest neighbour-based algorithm for P- and T-waves detection and delineation.

The aim of an automated Electrocardiogram (ECG) delineation system is the reliable detection of the characteristic waveforms and determination of peaks and limits of individual QRS-complex, P- and T-waves. In this paper, a classical statistical pattern recognition algorithm characterized with high accuracy and stability, i.e., K-Nearest Neighbour (KNN) has been proposed for locating the fiducial points along with their waveform boundaries in ECG signals. First, the QRS-complex along with its onset and offset points of each beat is detected from the ECG signal. After that P- and T-wave, relative to each QRS-complex along with their onset and offset points, are then identified using this algorithm. The feature extraction is done using the gradient of the ECG signals. The performance of the proposed algorithm has been evaluated on two standard manually annotated databases, (i) CSE and (ii) QT, and also on ECG data acquired using BIOPAC®MP100 system in laboratory settings. The results in terms of accuracy, i.e., 92.8% for CSE database obtained, clearly indicate a high degree of agreement with the manual annotations made by the referees of CSE dataset-3. Further, the delineation results of the CSE and QT database are compared with the accepted tolerances as recommended by the CSE working party. The results for ECG records acquired using the BIOPAC®MP100 system, in terms of QRS duration, heart rate, QT-interval, P-wave duration and PR-interval using KNN algorithm have also been computed.